Peer Revenue Now accepting positions

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Cryptography and Security

cs.CR Watch Cryptography and Security

Tuesday 13 January

Cryptography and Security

MASH: Evading Black-Box AI-Generated Text Detectors via Style Humanization

Yongtong Gu, Songze Li and Xia Hu

The increasing misuse of AI-generated texts (AIGT) has motivated the rapid development of AIGT detection methods. However, the reliability of these detectors remains fragile against adversarial evasions. Existing attack strategies often rely on white-box assumptions or demand prohibitively high computational and interaction costs, rendering them ineffective under practical black-box scenarios. In this paper, we propose Multi-stage Alignment for Style Humanization (MASH), a novel framework that evades black-box detectors based on style transfer. MASH sequentially employs style-injection supervised fine-tuning, direct preference optimization, and inference-time refinement to shape the distributions of AI-generated texts to resemble those of human-written texts. Experiments across 6 datasets and 5 detectors demonstrate the superior performance of MASH over 11 baseline evaders. Specifically, MASH achieves an average Attack Success Rate (ASR) of 92%, surpassing the strongest baselines by an average of 24%, while maintaining superior linguistic quality.
Read the full abstract

Cryptography and Security · Cross-listed from cs.CL

STAR: Detecting Inference-time Backdoors in LLM Reasoning via State-Transition Amplification Ratio

Seong-Gyu Park, Sohee Park, Jisu Lee et al. (+2 more)

Recent LLMs increasingly integrate reasoning mechanisms like Chain-of-Thought (CoT). However, this explicit reasoning exposes a new attack surface for inference-time backdoors, which inject malicious reasoning paths without altering model parameters. Because these attacks generate linguistically coherent paths, they effectively evade conventional detection. To address this, we propose STAR (State-Transition Amplification Ratio), a framework that detects backdoors by analyzing output probability shifts. STAR exploits the statistical discrepancy where a malicious input-induced path exhibits high posterior probability despite a low prior probability in the model's general knowledge. We quantify this state-transition amplification and employ the CUSUM algorithm to detect persistent anomalies. Experiments across diverse models (8B-70B) and five benchmark datasets demonstrate that STAR exhibits robust generalization capabilities, consistently achieving near-perfect performance (AUROC $\approx$ 1.0) with approximately $42\times$ greater efficiency than existing baselines. Furthermore, the framework proves robust against adaptive attacks attempting to bypass detection.
Read the full abstract

All authors Seong-Gyu Park, Sohee Park, Jisu Lee, Hyunsik Na, Daeseon Choi

Cryptography and Security

Baiting AI: Deceptive Adversary Against AI-Protected Industrial Infrastructures

Aryan Pasikhani, Prosanta Gope, Yang Yang et al. (+2 more)

This paper explores a new cyber-attack vector targeting Industrial Control Systems (ICS), particularly focusing on water treatment facilities. Developing a new multi-agent Deep Reinforcement Learning (DRL) approach, adversaries craft stealthy, strategically timed, wear-out attacks designed to subtly degrade product quality and reduce the lifespan of field actuators. This sophisticated method leverages DRL methodology not only to execute precise and detrimental impacts on targeted infrastructure but also to evade detection by contemporary AI-driven defence systems. By developing and implementing tailored policies, the attackers ensure their hostile actions blend seamlessly with normal operational patterns, circumventing integrated security measures. Our research reveals the robustness of this attack strategy, shedding light on the potential for DRL models to be manipulated for adversarial purposes. Our research has been validated through testing and analysis in an industry-level setup. For reproducibility and further study, all related materials, including datasets and documentation, are publicly accessible.
Read the full abstract

All authors Aryan Pasikhani, Prosanta Gope, Yang Yang, Shagufta Mehnaz, Biplab Sikdar

Cryptography and Security

On the Maximum Toroidal Distance Code for Lattice-Based Public-Key Cryptography

Shuiyin Liu and Amin Sakzad

We propose a maximum toroidal distance (MTD) code for lattice-based public-key encryption (PKE). By formulating the encryption encoding problem as the selection of $2^\ell$ points in the discrete $\ell$-dimensional torus $\mathbb{Z}_q^\ell$, the proposed construction maximizes the minimum $L_2$-norm toroidal distance to reduce the decryption failure rate (DFR) in post-quantum schemes such as the NIST ML-KEM (Crystals-Kyber). For $\ell = 2$, we show that the MTD code is essentially a variant of the Minal code recently introduced at IACR CHES 2025. For $\ell = 4$, we present a construction based on the $D_4$ lattice that achieves the largest known toroidal distance, while for $\ell = 8$, the MTD code corresponds to $2E_8$ lattice points in $\mathbb{Z}_4^8$. Numerical evaluations under the Kyber setting show that the proposed codes outperform both Minal and maximum Lee-distance ($L_1$-norm) codes in DFR for $\ell > 2$, while matching Minal code performance for $\ell = 2$.
Read the full abstract

Cryptography and Security · Cross-listed from cs.AI

WebTrap Park: An Automated Platform for Systematic Security Evaluation of Web Agents

Xinyi Wu, Jiagui Chen, Geng Hong et al. (+4 more)

Web Agents are increasingly deployed to perform complex tasks in real web environments, yet their security evaluation remains fragmented and difficult to standardize. We present WebTrap Park, an automated platform for systematic security evaluation of Web Agents through direct observation of their concrete interactions with live web pages. WebTrap Park instantiates three major sources of security risk into 1,226 executable evaluation tasks and enables action based assessment without requiring agent modification. Our results reveal clear security differences across agent frameworks, highlighting the importance of agent architecture beyond the underlying model. WebTrap Park is publicly accessible at https://security.fudan.edu.cn/webagent and provides a scalable foundation for reproducible Web Agent security evaluation.
Read the full abstract

All authors Xinyi Wu, Jiagui Chen, Geng Hong, Jiayi Dong, Xudong Pan, Jiarun Dai, Min Yang

Cryptography and Security · Cross-listed from cs.AR

A New Tool to Find Lightweight (And, Xor) Implementations of Quadratic Vectorial Boolean Functions up to Dimension 9

Marie Bolzer, Sébastien Duval and Marine Minier

The problem of finding a minimal circuit to implement a given function is one of the oldest in electronics. It is known to be NP-hard. Still, many tools exist to find sub-optimal circuits to implement a function. In electronics, such tools are known as synthesisers. However, these synthesisers aim to implement very large functions (a whole electronic chip). In cryptography, the focus is on small functions, hence the necessity for new dedicated tools for small functions. Several tools exist to implement small functions. They differ by their algorithmic approach (some are based on Depth-First-Search as introduced by Ullrich in 2011, some are based on SAT-solvers like the tool desgined by Stoffelen in 2016, some non-generic tools use subfield decomposition) and by their optimisation criteria (some optimise for circuit size, others for circuit depth, and some for side-channel-protected implementations). However, these tools are limited to functions operating on less than 5 bits, sometimes 6 bits for quadratic functions, or to very simple functions. The limitation lies in a high computing time. We propose a new tool (The tool is provided alongside the IEEE article with CodeOcean and at https://github.com/seduval/implem-quad-sbox) to implement quadratic functions up to 9 bits within AND-depth 1, minimising the number of AND gates. This tool is more time-efficient than previous ones, allowing to explore larger implementations than others on 6 bits or less and allows to reach larger sizes, up to 9 bits.
Read the full abstract

Cryptography and Security

APT-MCL: An Adaptive APT Detection System Based on Multi-View Collaborative Provenance Graph Learning

Mingqi Lv, Shanshan Zhang, Haiwen Liu et al. (+2 more)

Advanced persistent threats (APTs) are stealthy and multi-stage, making single-point defenses (e.g., malware- or traffic-based detectors) ill-suited to capture long-range and cross-entity attack semantics. Provenance-graph analysis has become a prominent approach for APT detection. However, its practical deployment is hampered by (i) the scarcity of APT samples, (ii) the cost and difficulty of fine-grained APT sample labeling, and (iii) the diversity of attack tactics and techniques. Aiming at these problems, this paper proposes APT-MCL, an intelligent APT detection system based on Multi-view Collaborative provenance graph Learning. It adopts an unsupervised learning strategy to discover APT attacks at the node level via anomaly detection. After that, it creates multiple anomaly detection sub-models based on multi-view features and integrates them within a collaborative learning framework to adapt to diverse attack scenarios. Extensive experiments on three real-world APT datasets validate the approach: (i) multi-view features improve cross-scenario generalization, and (ii) co-training substantially boosts node-level detection under label scarcity, enabling practical deployment on diverse attack scenarios.
Read the full abstract

All authors Mingqi Lv, Shanshan Zhang, Haiwen Liu, Tieming Chen, Tiantian Zhu

Cryptography and Security

A Survey of Security Challenges and Solutions for UAS Traffic Management (UTM) and small Unmanned Aerial Systems (sUAS)

Iman Sharifi, Mahyar Ghazanfari, Abenezer Taye et al. (+25 more)

The rapid growth of small Unmanned Aerial Systems (sUAS) for civil and commercial missions has intensified concerns about their resilience to cyber-security threats. Operating within the emerging UAS Traffic Management (UTM) framework, these lightweight and highly networked platforms depend on secure communication, navigation, and surveillance (CNS) subsystems that are vulnerable to spoofing, jamming, hijacking, and data manipulation. While prior reviews of UAS security addressed these challenges at a conceptual level, a detailed, system-oriented analysis for resource-constrained sUAS remains lacking. This paper presents a comprehensive survey of cyber-security vulnerabilities and defenses tailored to the sUAS and UTM ecosystem. We organize existing research across the full cyber-physical stack, encompassing CNS, data links, sensing and perception, UTM cloud access, and software integrity layers, and classify attack vectors according to their technical targets and operational impacts. Correspondingly, we review defense mechanisms ranging from classical encryption and authentication to adaptive intrusion detection, lightweight cryptography, and secure firmware management. By mapping threats to mitigation strategies and evaluating their scalability and practical effectiveness, this work establishes a unified taxonomy and identifies open challenges for achieving safe, secure, and scalable sUAS operations within future UTM environments.
Read the full abstract

All authors Iman Sharifi, Mahyar Ghazanfari, Abenezer Taye, Peng Wei, Maheed H. Ahmed, Hyeong Tae Kim, Mahsa Ghasemi, Vijay Gupta, Noah Dahle, Robert Canady, Abel Diaz Gonzalez, Austin Coursey, Bryce Bjorkman, Cailani Lemieux-Mack, Bryan C. Ward, Xenofon Koutsoukos, Gautam Biswas, Heber Herencia-Zapana, Saqib Hasan, Isaac Amundson, Filippos Fotiadis, Ufuk Topcu, Junchi Lu, Qi Alfred Chen, Nischal Aryal, Amer Ibrahim, Abdul Karim Ras, Amir Shirkhodaie

Cryptography and Security

DNF: Dual-Layer Nested Fingerprinting for Large Language Model Intellectual Property Protection

Zhenhua Xu, Yiran Zhao, Mengting Zhong et al. (+4 more)

The rapid growth of large language models raises pressing concerns about intellectual property protection under black-box deployment. Existing backdoor-based fingerprints either rely on rare tokens – leading to high-perplexity inputs susceptible to filtering – or use fixed trigger-response mappings that are brittle to leakage and post-hoc adaptation. We propose Dual-Layer Nested Fingerprinting (DNF), a black-box method that embeds a hierarchical backdoor by coupling domain-specific stylistic cues with implicit semantic triggers. Across Mistral-7B, LLaMA-3-8B-Instruct, and Falcon3-7B-Instruct, DNF achieves perfect fingerprint activation while preserving downstream utility. Compared with existing methods, it uses lower-perplexity triggers, remains undetectable under fingerprint detection attacks, and is relatively robust to incremental fine-tuning and model merging. These results position DNF as a practical, stealthy, and resilient solution for LLM ownership verification and intellectual property protection.
Read the full abstract

All authors Zhenhua Xu, Yiran Zhao, Mengting Zhong, Dezhang Kong, Changting Lin, Tong Qiao, Meng Han

Cryptography and Security · Cross-listed from cs.LG

One-Shot Federated Ridge Regression: Exact Recovery via Sufficient Statistic Aggregation

Zahir Alsulaimawi

Federated learning protocols require repeated synchronization between clients and a central server, with convergence rates depending on learning rates, data heterogeneity, and client sampling. This paper asks whether iterative communication is necessary for distributed linear regression. We show it is not. We formulate federated ridge regression as a distributed equilibrium problem where each client computes local sufficient statistics – the Gram matrix and moment vector – and transmits them once. The server reconstructs the global solution through a single matrix inversion. We prove exact recovery: under a coverage condition on client feature matrices, one-shot aggregation yields the centralized ridge solution, not an approximation. For heterogeneous distributions violating coverage, we derive non-asymptotic error bounds depending on spectral properties of the aggregated Gram matrix. Communication reduces from $\mathcal{O}(Rd)$ in iterative methods to $\mathcal{O}(d^2)$ total; for high-dimensional settings, we propose and experimentally validate random projection techniques reducing this to $\mathcal{O}(m^2)$ where $m \ll d$. We establish differential privacy guarantees where noise is injected once per client, eliminating the composition penalty that degrades privacy in multi-round protocols. We further address practical considerations including client dropout robustness, federated cross-validation for hyperparameter selection, and comparison with gradient-based alternatives. Comprehensive experiments on synthetic heterogeneous regression demonstrate that one-shot fusion matches FedAvg accuracy while requiring up to $38\times$ less communication. The framework applies to kernel methods and random feature models but not to general nonlinear architectures.
Read the full abstract

Cryptography and Security · Cross-listed from cs.CL

Evaluating Implicit Regulatory Compliance in LLM Tool Invocation via Logic-Guided Synthesis

Da Song, Yuheng Huang, Boqi Chen et al. (+4 more)

The integration of large language models (LLMs) into autonomous agents has enabled complex tool use, yet in high-stakes domains, these systems must strictly adhere to regulatory standards beyond simple functional correctness. However, existing benchmarks often overlook implicit regulatory compliance, thus failing to evaluate whether LLMs can autonomously enforce mandatory safety constraints. To fill this gap, we introduce LogiSafetyGen, a framework that converts unstructured regulations into Linear Temporal Logic oracles and employs logic-guided fuzzing to synthesize valid, safety-critical traces. Building on this framework, we construct LogiSafetyBench, a benchmark comprising 240 human-verified tasks that require LLMs to generate Python programs that satisfy both functional objectives and latent compliance rules. Evaluations of 13 state-of-the-art (SOTA) LLMs reveal that larger models, despite achieving better functional correctness, frequently prioritize task completion over safety, which results in non-compliant behavior.
Read the full abstract

All authors Da Song, Yuheng Huang, Boqi Chen, Tianshuo Cong, Randy Goebel, Lei Ma, Foutse Khomh

Cryptography and Security

ForgetMark: Stealthy Fingerprint Embedding via Targeted Unlearning in Language Models

Zhenhua Xu, Haobo Zhang, Zhebo Wang et al. (+4 more)

Existing invasive (backdoor) fingerprints suffer from high-perplexity triggers that are easily filtered, fixed response patterns exposed by heuristic detectors, and spurious activations on benign inputs. We introduce ForgetMark, a stealthy fingerprinting framework that encodes provenance via targeted unlearning. It builds a compact, human-readable key–value set with an assistant model and predictive-entropy ranking, then trains lightweight LoRA adapters to suppress the original values on their keys while preserving general capabilities. Ownership is verified under black/gray-box access by aggregating likelihood and semantic evidence into a fingerprint success rate. By relying on probabilistic forgetting traces rather than fixed trigger–response patterns, ForgetMark avoids high-perplexity triggers, reduces detectability, and lowers false triggers. Across diverse architectures and settings, it achieves 100% ownership verification on fingerprinted models while maintaining standard performance, surpasses backdoor baselines in stealthiness and robustness to model merging, and remains effective under moderate incremental fine-tuning. Our code and data are available at \href{https://github.com/Xuzhenhua55/ForgetMark}{https://github.com/Xuzhenhua55/ForgetMark}.
Read the full abstract

All authors Zhenhua Xu, Haobo Zhang, Zhebo Wang, Qichen Liu, Haitao Xu, Wenpeng Xing, Meng Han

Cryptography and Security

Decentralized Firmware Integrity Verification for Cyber-Physical Systems Using Ethereum Blockchain

S M Mostaq Hossain and Amani Altarawneh

Firmware integrity is a foundational requirement for securing Cyber-Physical Systems (CPS), where malicious or compromised firmware can result in persistent backdoors, unauthorized control, or catastrophic system failures. Traditional verification mechanisms such as secure boot, digital signatures, and centralized hash databases are increasingly inadequate due to risks from insider threats and single points of failure. In this paper, we propose a decentralized firmware integrity verification framework built on the Ethereum blockchain, offering tamperproof, transparent, and trustless validation. Our system stores SHA-256 hashes of firmware binaries within smart contracts deployed on the Ethereum Sepolia testnet, using Web3 and Infura for seamless on-chain interaction. A Python-based client tool computes firmware hashes and communicates with the blockchain to register and verify firmware authenticity in realtime. We implement and evaluate a fully functional prototype using real firmware samples, demonstrating successful contract deployment, hash registration, and integrity verification through live blockchain transactions. Experimental results confirm the reliability and low cost (in gas fees) of our approach, highlighting its practicality and scalability for real-world CPS applications. To enhance scalability and performance, we discuss extensions using Layer-2 rollups and off-chain storage via the InterPlanetary File System (IPFS). We also outline integration pathways with secure boot mechanisms, Trusted Platform Module (TPM)based attestation, and zero-trust architectures. This work contributes a practical and extensible model for blockchain-based firmware verification, significantly strengthening the defense against firmware tampering and supply chain attacks in critical CPS environments.
Read the full abstract

Monday 12 January

Cryptography and Security

Instalación, configuración y utilización de un nodo Bitcoin en Linux

Jose Eduardo Ulloa and Diego R. Llanos

This paper documents the installation, configuration, and operation of a full Bitcoin node in a Linux environment, from manual compilation of the source code to complete synchronization with the network. The technical phases of the process are described, the main files generated by Bitcoin Core are analyzed, and the effects of the parameters txindex, prune, dbcache, maxmempool, and maxconnections are empirically studied. System resources during the block download (IBD) mechanism are also documented, and the operational importance of each resource is explained. This paper provides a solid foundation for future research proposals on Bitcoin node performance or for the development of blockchain data query tools.
Read the full abstract

Cryptography and Security

False Friends in the Shell: Unveiling the Emoticon Semantic Confusion in Large Language Models

Weipeng Jiang, Xiaoyu Zhang, Juan Zhai et al. (+3 more)

Emoticons are widely used in digital communication to convey affective intent, yet their safety implications for Large Language Models (LLMs) remain largely unexplored. In this paper, we identify emoticon semantic confusion, a vulnerability where LLMs misinterpret ASCII-based emoticons to perform unintended and even destructive actions. To systematically study this phenomenon, we develop an automated data generation pipeline and construct a dataset containing 3,757 code-oriented test cases spanning 21 meta-scenarios, four programming languages, and varying contextual complexities. Our study on six LLMs reveals that emoticon semantic confusion is pervasive, with an average confusion ratio exceeding 38%. More critically, over 90% of confused responses yield 'silent failures', which are syntactically valid outputs but deviate from user intent, potentially leading to destructive security consequences. Furthermore, we observe that this vulnerability readily transfers to popular agent frameworks, while existing prompt-based mitigations remain largely ineffective. We call on the community to recognize this emerging vulnerability and develop effective mitigation methods to uphold the safety and reliability of the LLM system.
Read the full abstract

All authors Weipeng Jiang, Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Chao Shen, Yang Liu

Cryptography and Security

SecureCAI: Injection-Resilient LLM Assistants for Cybersecurity Operations

Mohammed Himayath Ali, Mohammed Aqib Abdullah, Mohammed Mudassir Uddin et al. (+1 more)

Large Language Models have emerged as transformative tools for Security Operations Centers, enabling automated log analysis, phishing triage, and malware explanation; however, deployment in adversarial cybersecurity environments exposes critical vulnerabilities to prompt injection attacks where malicious instructions embedded in security artifacts manipulate model behavior. This paper introduces SecureCAI, a novel defense framework extending Constitutional AI principles with security-aware guardrails, adaptive constitution evolution, and Direct Preference Optimization for unlearning unsafe response patterns, addressing the unique challenges of high-stakes security contexts where traditional safety mechanisms prove insufficient against sophisticated adversarial manipulation. Experimental evaluation demonstrates that SecureCAI reduces attack success rates by 94.7% compared to baseline models while maintaining 95.1% accuracy on benign security analysis tasks, with the framework incorporating continuous red-teaming feedback loops enabling dynamic adaptation to emerging attack strategies and achieving constitution adherence scores exceeding 0.92 under sustained adversarial pressure, thereby establishing a foundation for trustworthy integration of language model capabilities into operational cybersecurity workflows and addressing a critical gap in current approaches to AI safety within adversarial domains.
Read the full abstract

All authors Mohammed Himayath Ali, Mohammed Aqib Abdullah, Mohammed Mudassir Uddin, Shahnawaz Alam

Cryptography and Security

TeeMAF: A TEE-Based Mutual Attestation Framework for On-Chain and Off-Chain Functions in Blockchain DApps

Xiangyu Liu, Brian Lee and Yuansong Qiao

The rapid development of Internet of Things (IoT) technology has led to growing concerns about data security and user privacy in the interactions within distributed systems. Decentralized Applications (DApps) in distributed systems consist of on-chain and off-chain functions, where on-chain functions are smart contracts running in the blockchain network, while off-chain functions operate outside the blockchain. Since smart contracts cannot access off-chain information, they cannot verify whether the off-chain functions, i.e. the software components, they interact with have been tampered or not. As a result, establishing mutual trust between the on-chain smart contracts and the off-chain functions remains a significant challenge. To address the challenge, this paper introduces TeeMAF, a generic framework for mutual attestation between on-chain and off-chain functions, leveraging Trusted Execution Environments (TEE), specifically Intel Software Guard Extensions (SGX), SCONE (a TEE container on top of Intel SGX), and remote attestation technologies. This ensures that the deployed off-chain functions of a DApp execute in a provably secure computing environment and achieve mutual attestation with the interacting on-chain functions. Through a security analysis of TeeMAF, the reliability of deployed DApps can be verified, ensuring their correct execution. Furthermore, based on this framework, this paper proposes a decentralized resource orchestration platform (a specific DApp) for deploying applications over untrusted environments. The system is implemented on Ethereum and benchmarked using Hyperledger Caliper. Performance evaluation focusing on throughput and latency demonstrates that, compared to platforms without a mutual attestation scheme, the performance overhead remains within an acceptable range.
Read the full abstract

Cryptography and Security

Towards Automating Blockchain Consensus Verification with IsabeLLM

Elliot Jones and William Knottenbelt

Consensus protocols are crucial for a blockchain system as they are what allow agreement between the system's nodes in a potentially adversarial environment. For this reason, it is paramount to ensure their correct design and implementation to prevent such adversaries from carrying out malicious behaviour. Formal verification allows us to ensure the correctness of such protocols, but requires high levels of effort and expertise to carry out and thus is often omitted in the development process. In this paper, we present IsabeLLM, a tool that integrates the proof assistant Isabelle with a Large Language Model to assist and automate proofs. We demonstrate the effectiveness of IsabeLLM by using it to develop a novel model of Bitcoin's Proof of Work consensus protocol and verify its correctness. We use the DeepSeek R1 API for this demonstration and found that we were able to generate correct proofs for each of the non-trivial lemmas present in the verification.
Read the full abstract

Cryptography and Security

Hagenberg Risk Management Process (Part 1): Multidimensional Polar Heatmaps for Context-Sensitive Risk Analysis

Eckehard Hermann and Harald Lampesberger

Traditional two-dimensional risk matrices (heatmaps) are widely used to model and visualize likelihood and impact relationships, but they face fundamental methodological limitations when applied to complex infrastructures. In particular, regulatory frameworks such as NIS2 and DORA call for more context-sensitive and system-oriented risk analysis. We argue that incorporating contextual dimensions into heatmaps enhances their analytical value. As a first step towards our Hagenberg Risk Management Process for complex infrastructures and systems, this paper introduces a multidimensional (ND) polar heatmap as a formal model that explicitly integrates additional context dimensions and subsumes classical two-dimensional models as a special case.
Read the full abstract

Cryptography and Security

Simple Power Analysis of Polynomial Multiplication in HQC

Pavel Velek, Tomáš Rabas and Jiří Buček

The Hamming Quasi-Cyclic (HQC) cryptosystem was selected for standardization in the fourth round of the NIST Post-Quantum Cryptography (PQC) standardization project. The goal of the PQC project is to standardize one or more quantum-resistant public-key cryptographic algorithms. In this paper, we present a single-trace Simple Power Analysis (SPA) attack against HQC that exploits power consumption leakage that occurs during polynomial multiplication performed at the beginning of HQC decryption. Using the ChipWhisperer-Lite board, we perform and evaluate the attack, achieving a 99.69% success rate over 10 000 attack attempts. We also propose various countermeasures against the attack and evaluate their time complexity.
Read the full abstract

Cryptography and Security

A Protocol-Aware P4 Pipeline for MQTT Security and Anomaly Mitigation in Edge IoT Systems

Bui Ngoc Thanh Binh, Pham Hoai Luan, Le Vu Trung Duong et al. (+2 more)

MQTT is the dominant lightweight publish–subscribe protocol for IoT deployments, yet edge security remains inadequate. Cloud-based intrusion detection systems add latency that is unsuitable for real-time control, while CPU-bound firewalls and generic SDN controllers lack MQTT awareness to enforce session validation, topic-based authorization, and behavioral anomaly detection. We propose a P4-based data-plane enforcement scheme for protocol-aware MQTT security and anomaly detection at the network edge. The design combines parser-safe MQTT header extraction with session-order validation, byte-level topic-prefix authorization with per-client rate limiting and soft-cap enforcement, and lightweight anomaly detection based on KeepAlive and Remaining Length screening with clone-to-CPU diagnostics. The scheme leverages stateful primitives in BMv2 (registers, meters, direct counters) to enable runtime policy adaptation with minimal per-packet latency. Experiments on a Mininet/BMv2 testbed demonstrate high policy enforcement accuracy (99.8%, within 95% CI), strong anomaly detection sensitivity (98% true-positive rate), and high delivery >99.9% for 100–5~kpps; 99.8% at 10~kpps; 99.6% at 16~kpps) with sub-millisecond per-packet latency. These results show that protocol-aware MQTT filtering can be efficiently realized in the programmable data plane, providing a practical foundation for edge IoT security. Future work will validate the design on production P4 hardware and integrate machine learning–based threshold adaptation.
Read the full abstract

All authors Bui Ngoc Thanh Binh, Pham Hoai Luan, Le Vu Trung Duong, Vu Tuan Hai, Yasuhiko Nakashima

Cryptography and Security

Principal ideal problem and ideal shortest vector over rational primes in power-of-two cyclotomic fields

Gaohao Cui, Jianing Li and Jincheng Zhuang

The shortest vector problem (SVP) over ideal lattices is closely related to the Ring-LWE problem, which is widely used to build post-quantum cryptosystems. Power-of-two cyclotomic fields are frequently adopted to instantiate Ring-LWE. Pan et al. (EUROCRYPT~2021) explored the SVP over ideal lattices via the decomposition fields and, in particular determined the length of the shortest vector in prime ideals lying over rational primes $p\equiv3,5\pmod{8}$ in power-of-two cyclotomic fields via explicit construction of reduced lattice bases. In this work, we first provide a new method (different from analyzing lattice bases) to analyze the length of the shortest vector in prime ideals in $\mathbb{Z}[\zeta_{2^{n+1}}]$ when $p\equiv3,5\pmod{8}$. Then we precisely characterize the length of the shortest vector in the cases of $p\equiv7,9\pmod{16}$. Furthermore, we derive a new upper bound $\sqrt[4]{2^{2n+1}p}$ for this length, which is tighter than the bound $2^n\sqrt[4]{p}$ obtained from Minkowski's theorem. Our key technique is to investigate whether a generator of a principal ideal can achieve the shortest length after embedding as a vector. If this holds for the ideal, finding the shortest vector in this ideal can be reduced to finding its shortest generator.
Read the full abstract

Cryptography and Security

Peacock: UEFI Firmware Runtime Observability Layer for Detection and Response

Hadar Cochavi Gorelik, Orel Fadlon, Denis Klimov et al. (+3 more)

Modern computing platforms rely on the Unified Extensible Firmware Interface (UEFI) to initialize hardware and coordinate the transition to the operating system. Because this execution environment operates with high privileges and persists across reboots, it has increasingly become a target for advanced threats, including bootkits documented in real systems. Existing protections, including Secure Boot and static signature verification, are insufficient against adversaries who exploit runtime behavior or manipulate firmware components after signature checks have completed. In contrast to operating system (OS) environments, where mature tools provide dynamic inspection and incident response, the pre-OS stage lacks practical mechanisms for real-time visibility and threat detection. We present Peacock, a modular framework that introduces integrity-assured monitoring and remote verification for the UEFI boot process. Peacock consists of three components: (i) a UEFI-based agent that records Boot and Runtime Service activity with cryptographic protection against tampering; (ii) a cross-platform OS Agent that extracts the recorded measurements and produces a verifiable attestation bundle using hardware-backed guarantees from the platform's trusted module; and (iii) a Peacock Server that verifies attestation results and exports structured telemetry for enterprise detection. Our evaluation shows that Peacock reliably detects multiple real-world UEFI bootkits, including Glupteba, BlackLotus, LoJax, and MosaicRegressor. Taken together, these results indicate that Peacock provides practical visibility and verification capabilities within the firmware layer, addressing threats that bypass traditional OS-level security mechanisms.
Read the full abstract

All authors Hadar Cochavi Gorelik, Orel Fadlon, Denis Klimov, Oleg Brodt, Asaf Shabtai, Yuval Elovici

Cryptography and Security

MCP-ITP: An Automated Framework for Implicit Tool Poisoning in MCP

Ruiqi Li, Zhiqiang Wang, Yunhao Yao et al. (+1 more)

To standardize interactions between LLM-based agents and their environments, the Model Context Protocol (MCP) was proposed and has since been widely adopted. However, integrating external tools expands the attack surface, exposing agents to tool poisoning attacks. In such attacks, malicious instructions embedded in tool metadata are injected into the agent context during MCP registration phase, thereby manipulating agent behavior. Prior work primarily focuses on explicit tool poisoning or relied on manually crafted poisoned tools. In contrast, we focus on a particularly stealthy variant: implicit tool poisoning, where the poisoned tool itself remains uninvoked. Instead, the instructions embedded in the tool metadata induce the agent to invoke a legitimate but high-privilege tool to perform malicious operations. We propose MCP-ITP, the first automated and adaptive framework for implicit tool poisoning within the MCP ecosystem. MCP-ITP formulates poisoned tool generation as a black-box optimization problem and employs an iterative optimization strategy that leverages feedback from both an evaluation LLM and a detection LLM to maximize Attack Success Rate (ASR) while evading current detection mechanisms. Experimental results on the MCPTox dataset across 12 LLM agents demonstrate that MCP-ITP consistently outperforms the manually crafted baseline, achieving up to 84.2% ASR while suppressing the Malicious Tool Detection Rate (MDR) to as low as 0.3%.
Read the full abstract

All authors Ruiqi Li, Zhiqiang Wang, Yunhao Yao, Xiang-Yang Li

Cryptography and Security

Examining the Effectiveness of Transformer-Based Smart Contract Vulnerability Scan

Emre Balci, Timucin Aydede, Gorkem Yilmaz et al. (+1 more)

Smart contract technology facilitates self-executing agreements on the blockchain, eliminating dependency on an external trusted authority. However, smart contracts may expose vulnerabilities that can lead to financial losses and disruptions in decentralized applications. In this work, we evaluate deep learning-based approaches for vulnerability scanning of Ethereum smart contracts. We propose VASCOT, a Vulnerability Analyzer for Smart COntracts using Transformers, which performs sequential analysis of Ethereum Virtual Machine (EVM) bytecode and incorporates a sliding window mechanism to overcome input length constraints. To assess VASCOT's detection efficacy, we construct a dataset of 16,469 verified Ethereum contracts deployed in 2022, and annotate it using trace analysis with concrete validation to mitigate false positives. VASCOT's performance is then compared against a state-of-the-art LSTM-based vulnerability detection model on both our dataset and an older public dataset. Our findings highlight the strengths and limitations of each model, providing insights into their detection capabilities and generalizability.
Read the full abstract

All authors Emre Balci, Timucin Aydede, Gorkem Yilmaz, Ece Gelal Soyak

Cryptography and Security

Memory-Based Malware Detection under Limited Data Conditions: A Comparative Evaluation of TabPFN and Ensemble Models

Valentin Leroy, Shuvalaxmi Dass and Sharif Ullah

Artificial intelligence and machine learning have significantly advanced malware research by enabling automated threat detection and behavior analysis. However, the availability of exploitable data is limited, due to the absence of large datasets with real-world data. Despite the progress of AI in cybersecurity, malware analysis still suffers from this data scarcity, which limits model generalization. In order to tackle this difficulty, this workinvestigates TabPFN, a learning-free model designed for low-data regimes. We evaluate its performance against established baselines such as Random Forest, LightGBM and XGBoost, across multiple class configurations. Our experimental results indicate that TabPFN surpasses all other models in low-data regimes, with a 2% to 6% improvement observed across multiple performance metrics. However, this increase in performance has an impact on its computation time in a particular case. These findings highlight both the promise and the practical limitations of integrating TabPFN into cybersecurity workflows.
Read the full abstract

Cryptography and Security

A High-Recall Cost-Sensitive Machine Learning Framework for Real-Time Online Banking Transaction Fraud Detection

Karthikeyan V. R., Premnath S., Kavinraaj S. et al. (+1 more)

Fraudulent activities on digital banking services are becoming more intricate by the day, challenging existing defenses. While older rule driven methods struggle to keep pace, even precision focused algorithms fall short when new scams are introduced. These tools typically overlook subtle shifts in criminal behavior, missing crucial signals. Because silent breaches cost institutions far more than flagged but legitimate actions, catching every possible case is crucial. High sensitivity to actual threats becomes essential when oversight leads to heavy losses. One key aim here involves reducing missed fraud cases without spiking incorrect alerts too much. This study builds a system using group learning methods adjusted through smart threshold choices. Using real world transaction records shared openly, where cheating acts rarely appear among normal activities, tests are run under practical skewed distributions. The outcomes reveal that approximately 98 percent of actual fraud is detected, outperforming standard setups that rely on unchanging rules when dealing with uneven examples across classes. When tested in live settings, the fraud detection system connects directly to an online banking transaction flow, stopping questionable activities before they are completed. Alongside this setup, a browser add on built for Chrome is designed to flag deceptive web links and reduce threats from harmful sites. These results show that adjusting decisions by cost impact and validating across entire systems makes deployment more stable and realistic for today's digital banking platforms.
Read the full abstract

All authors Karthikeyan V. R., Premnath S., Kavinraaj S., J. Sangeetha

Cryptography and Security

When Bots Take the Bait: Exposing and Mitigating the Emerging Social Engineering Attack in Web Automation Agent

Xinyi Wu, Geng Hong, Yueyue Chen et al. (+5 more)

Web agents, powered by large language models (LLMs), are increasingly deployed to automate complex web interactions. The rise of open-source frameworks (e.g., Browser Use, Skyvern-AI) has accelerated adoption, but also broadened the attack surface. While prior research has focused on model threats such as prompt injection and backdoors, the risks of social engineering remain largely unexplored. We present the first systematic study of social engineering attacks against web automation agents and design a pluggable runtime mitigation solution. On the attack side, we introduce the AgentBait paradigm, which exploits intrinsic weaknesses in agent execution: inducement contexts can distort the agent's reasoning and steer it toward malicious objectives misaligned with the intended task. On the defense side, we propose SUPERVISOR, a lightweight runtime module that enforces environment and intention consistency alignment between webpage context and intended goals to mitigate unsafe operations before execution. Empirical results show that mainstream frameworks are highly vulnerable to AgentBait, with an average attack success rate of 67.5% and peaks above 80% under specific strategies (e.g., trusted identity forgery). Compared with existing lightweight defenses, our module can be seamlessly integrated across different web automation frameworks and reduces attack success rates by up to 78.1% on average while incurring only a 7.7% runtime overhead and preserving usability. This work reveals AgentBait as a critical new threat surface for web agents and establishes a practical, generalizable defense, advancing the security of this rapidly emerging ecosystem. We reported the details of this attack to the framework developers and received acknowledgment before submission.
Read the full abstract

All authors Xinyi Wu, Geng Hong, Yueyue Chen, MingXuan Liu, Feier Jin, Xudong Pan, Jiarun Dai, Baojun Liu

Cryptography and Security · Cross-listed from cs.CV

Universal Adversarial Purification with DDIM Metric Loss for Stable Diffusion

Li Zheng, Liangbin Xie, Jiantao Zhou et al. (+1 more)

Stable Diffusion (SD) often produces degraded outputs when the training dataset contains adversarial noise. Adversarial purification offers a promising solution by removing adversarial noise from contaminated data. However, existing purification methods are primarily designed for classification tasks and fail to address SD-specific adversarial strategies, such as attacks targeting the VAE encoder, UNet denoiser, or both. To address the gap in SD security, we propose Universal Diffusion Adversarial Purification (UDAP), a novel framework tailored for defending adversarial attacks targeting SD models. UDAP leverages the distinct reconstruction behaviors of clean and adversarial images during Denoising Diffusion Implicit Models (DDIM) inversion to optimize the purification process. By minimizing the DDIM metric loss, UDAP can effectively remove adversarial noise. Additionally, we introduce a dynamic epoch adjustment strategy that adapts optimization iterations based on reconstruction errors, significantly improving efficiency without sacrificing purification quality. Experiments demonstrate UDAP's robustness against diverse adversarial methods, including PID (VAE-targeted), Anti-DreamBooth (UNet-targeted), MIST (hybrid), and robustness-enhanced variants like Anti-Diffusion (Anti-DF) and MetaCloak. UDAP also generalizes well across SD versions and text prompts, showcasing its practical applicability in real-world scenarios.
Read the full abstract

All authors Li Zheng, Liangbin Xie, Jiantao Zhou, He YiMin

Cryptography and Security

BlindU: Blind Machine Unlearning without Revealing Erasing Data

Weiqi Wang, Zhiyi Tian, Chenhan Zhang et al. (+1 more)

Machine unlearning enables data holders to remove the contribution of their specified samples from trained models to protect their privacy. However, it is paradoxical that most unlearning methods require the unlearning requesters to firstly upload their data to the server as a prerequisite for unlearning. These methods are infeasible in many privacy-preserving scenarios where servers are prohibited from accessing users' data, such as federated learning (FL). In this paper, we explore how to implement unlearning under the condition of not uncovering the erasing data to the server. We propose Blind Unlearning (BlindU), which carries out unlearning using compressed representations instead of original inputs. BlindU only involves the server and the unlearning user: the user locally generates privacy-preserving representations, and the server performs unlearning solely on these representations and their labels. For the FL model training, we employ the information bottleneck (IB) mechanism. The encoder of the IB-based FL model learns representations that distort maximum task-irrelevant information from inputs, allowing FL users to generate compressed representations locally. For effective unlearning using compressed representation, BlindU integrates two dedicated unlearning modules tailored explicitly for IB-based models and uses a multiple gradient descent algorithm to balance forgetting and utility retaining. While IB compression already provides protection for task-irrelevant information of inputs, to further enhance the privacy protection, we introduce a noise-free differential privacy (DP) masking method to deal with the raw erasing data before compressing. Theoretical analysis and extensive experimental results illustrate the superiority of BlindU in privacy protection and unlearning effectiveness compared with the best existing privacy-preserving unlearning benchmarks.
Read the full abstract

All authors Weiqi Wang, Zhiyi Tian, Chenhan Zhang, Shui Yu