Papers

Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and enterprise automation. OpenClaw is a visible instance of this broader class. Without much attention yet, their security challenge is fundamentally different from that of traditional software that relies on predictable execution and well-defined control flow. In open agentic systems, everything is ”probabilistic”: plans are generated at runtime, key decisions may be shaped by untrusted natural-language inputs and tool outputs, execution unfolds in uncertain environments, and actions are taken under authority delegated by human users. The central challenge is therefore not merely robustness against individual attacks, but the governance of agentic behavior under persistent uncertainty. This paper systematizes the area through a software engineering lens. We introduce a six-dimensional analytical taxonomy and synthesize 50 papers spanning attacks, benchmarks, defenses, audits, and adjacent engineering foundations. From this synthesis, we derive a reference doctrine for secure-by-construction agent platforms, together with an evaluation scorecard for assessing platform security posture. Our review shows that the literature is relatively mature in attack characterization and benchmark construction, but remains weak in deployment controls, operational governance, persistent-memory integrity, and capability revocation. These gaps define a concrete engineering agenda for building agent ecosystems that are governable, auditable, and resilient under compromise.

With the continuous advancement of intelligent vehicle technology, the image data generated by vehicles has become increasingly critical in various applications, including driver assistance, traffic monitoring, and safety warning systems. However, this growing reliance on image data also raises pressing concerns regarding its security and privacy protection. Searchable encryption technology, as an effective means to protect data security, shows significant potential for application in the field of intelligent vehicles. In this paper, we propose a novel Privacy-pReserving Image Searchable Encryption Scheme (PRISE) to address the security and privacy challenges associated with image data in intelligent vehicles. The PRISE scheme employs Multilinear Principal Component Analysis (MPCA) to extract data features and integrates symmetric encryption and matrix encryption techniques to ensure image privacy protection. To enhance search efficiency, we utilize a Mahalanobis distance-based fuzzy C-means (FCM) clustering method, which accelerates the search process on the cloud server. We conducted comprehensive experiments to evaluate our proposed scheme, and the results were consistent with our analytical findings, confirming the security of our approach. Comparative experiments with existing schemes demonstrated that our proposed method achieves higher accuracy while maintaining a comparable query time.

Diffusion models generate high-quality images but pose serious risks like copyright violation and disinformation. Watermarking is a key defense for tracing and authenticating AI-generated content. However, existing methods rely on threshold-based detection, which only supports fuzzy matching and cannot recover structured watermark data bit-exactly, making them unsuitable for offline verification or applications requiring lossless metadata (e.g., licensing instructions). To address this problem, in this paper, we propose Gaussian Shannon, a watermarking framework that treats the diffusion process as a noisy communication channel and enables both robust tracing and exact bit recovery. Our method embeds watermarks in the initial Gaussian noise without fine-tuning or quality loss. We identify two types of channel interference, namely local bit flips and global stochastic distortions, and design a cascaded defense combining error-correcting codes and majority voting. This ensures reliable end-to-end transmission of semantic payloads. Experiments across three Stable Diffusion variants and seven perturbation types show that Gaussian Shannon achieves state-of-the-art bit-level accuracy while maintaining a high true positive rate, enabling trustworthy rights attribution in real-world deployment. The source code have been made available at: https://github.com/Rambo-Yi/Gaussian-Shannon

Safety-critical domains like healthcare rely on deep neural networks (DNNs) for prediction, yet DNNs remain vulnerable to evasion attacks. Anomaly detectors (ADs) are widely used to protect DNNs, but conventional ADs are trained indiscriminately on benign data from all patients, overlooking physiological differences that introduce noise, degrade robustness, and reduce recall. In this paper, we propose ROAST, a novel risk-aware outlier exposure (OE) selective training framework that improves AD recall while largely preserving precision. ROAST identifies patients who are less vulnerable to attack and focuses training on these cleaner, more reliable data, thereby reducing false negatives and improving recall. To preserve precision, the framework applies OE by injecting adversarial samples into the training set of the less vulnerable patients, avoiding noisy data from others. Experiments show that ROAST increases recall by 16.2% (black-box attack setting) and 5.89% (white-box attack setting) on average while reducing the training time by 88.3% on average compared to indiscriminate training, with minimal impact on precision.

Retrieval-Augmented Generation (RAG) enhances the utility of Large Language Models (LLMs) by retrieving external documents. Since the knowledge databases in RAG are predominantly utilized via cloud services, private data in sensitive domains such as finance and healthcare faces the risk of personal information leakage. Thus, effectively anonymizing knowledge bases is crucial for privacy preservation. Existing studies equate the privacy risk of text to the linear superposition of the privacy risks of individual, isolated sensitive entities. The "one-size-fits-all" full processing of all sensitive entities severely degrades utility of LLM. To address this issue, we introduce a dynamic anonymization framework named TRIP-RAG. Based on context-aware entity quantification, this framework evaluates entities from the perspectives of marginal privacy risk, knowledge divergence, and topical relevance. It identifies highly sensitive entities while trading off utility, providing a feasible approach for variable-intensity privacy protection scenarios. Our theoretical analysis and experiments indicate that TRIP-RAG can effectively reduce context inference risks. Extensive experimental results demonstrate that, while maintaining privacy protection comparable to full anonymization, TRIP-RAG's Recall@k decreases by less than 35% compared to the original data, and the generation quality improves by up to 56% over existing baselines.

Large Language Models (LLMs) generate responses based on user prompts. Often, these prompts may contain highly sensitive information, including personally identifiable information (PII), which could be exposed to third parties hosting these models. In this work, we propose a new method to sanitize user prompts. Our mechanism uses the randomized response mechanism of differential privacy to randomly and independently perturb each character in a word. The perturbed text is then sent to a remote LLM, which first performs a prompt restoration and subsequently performs the intended downstream task. The idea is that the restoration will be able to reconstruct non-sensitive words even when they are perturbed due to cues from the context, as well as the fact that these words are often very common. On the other hand, perturbation would make reconstruction of sensitive words difficult because they are rare. We experimentally validate our method on two datasets, i2b2/UTHealth and Enron, using two LLMs: Llama-3.1 8B Instruct and GPT-4o mini. We also compare our approach with a word-level differentially private mechanism, and with a rule-based PII redaction baseline, using a unified privacy-utility evaluation. Our results show that sensitive PII tagged in these datasets are reconstructed at a rate close to the theoretical rate of reconstructing completely random words, whereas non-sensitive words are reconstructed at a much higher rate. Our method has the advantage that it can be applied without explicitly identifying sensitive pieces of information in the prompt, while showing a good privacy-utility tradeoff for downstream tasks.

Open-source software supply chain security relies heavily on assessing affected versions of library vulnerabilities. While prior studies have leveraged exploits for verifying vulnerability affected versions, they point out a key limitation that exploits are version-specific and cannot be directly applied across library versions. Despite being widely acknowledged, this limitation has not been systematically validated at scale, leaving the actual applicability of exploits across versions unexplored. To fill this gap, we conduct the first large-scale empirical study on exploit applicability across library versions. We construct a comprehensive dataset consisting of 259 exploits spanning 128 Java libraries and 28,150 historical versions, covering 61 CWEs that account for 76.33% of vulnerabilities in Maven. Leveraging this dataset, we execute each exploit against the library version history and compare the execution outcomes with our manually annotated ground-truth affected versions. We further investigate the root causes of inconsistencies between exploit execution and ground truth, and explore strategies for exploit migration. Our results (RQ1) show that, even without migration, exploits achieve 83.0% recall and 99.3% precision in identifying affected versions in Java, outperforming most widely used vulnerability databases and assessment tools. Notably, this capability enables us to contribute 796 confirmed missing affected versions to the CPE dictionary. We investigate the remaining exploit failures (RQ2) and find that they mainly stem from compatibility issues introduced by library evolution and changing environmental constraints. Based on these observations, we manually migrate exploits for 1,885 versions and distill a taxonomy of 10 strategies from these successful adaptation cases (RQ3), thereby increasing the overall recall to 96.1%.

Concept erasure in text-to-image diffusion models seeks to remove undesired concepts while preserving overall generative capability. Localized erasure methods aim to restrict edits to the spatial region occupied by the target concept. However, we observe that suppressing a concept can unintentionally weaken semantically related neighbor concepts, reducing fidelity in fine-grained domains. We propose Neighbor-Aware Localized Concept Erasure (NLCE), a training-free framework designed to better preserve neighboring concepts while removing target concepts. It operates in three stages: (1) a spectrally-weighted embedding modulation that attenuates target concept directions while stabilizing neighbor concept representations, (2) an attention-guided spatial gate that identifies regions exhibiting residual concept activation, and (3) a spatially-gated hard erasure that eliminates remaining traces only where necessary. This neighbor-aware pipeline enables localized concept removal while maintaining the surrounding concept neighborhood structure. Experiments on fine-grained datasets (Oxford Flowers, Stanford Dogs) show that our method effectively removes target concepts while better preserving closely related categories. Additional results on celebrity identity, explicit content and artistic style demonstrate robustness and generalization to broader erasure scenarios.

Recent events surrounding the relationship between frontier AI suppliers and national-security customers have made a structural problem newly visible: once a privately governed model becomes embedded in military workflows, the supplier can influence not only technical performance but also the operational boundary conditions under which the system may be used. This paper argues that the central strategic issue is not merely access to capable models, but preservation of decision sovereignty: the state's ability to retain authority over decision policy, version control, fallback behavior, auditability, and final action approval even when analytical modules are sourced from commercial vendors. Using the public Anthropic–Pentagon dispute of 2026, the broader history of Project Maven, and recent U.S., NATO, U.K., and intelligence-community guidance as a motivating context, the paper develops a trade-secret-safe architectural formulation of the Energetic Paradigm as a layered, model-agnostic command-support design. In this formulation, supplier models remain replaceable analytical components, while routing, constraints, logging, escalation, and action authorization remain state-owned functions. The paper contributes three things: a definition of decision sovereignty for military AI; a threat model for supplier-induced boundary control; and a public architectural specification showing how model replaceability, human authority, and sovereign orchestration can reduce strategic dependency without requiring disclosure of proprietary implementation details. The argument is conceptual rather than experimental, but it yields concrete implications for procurement, governance, and alliance interoperability.

Physically Unclonable Functions (PUFs) provide promising hardware security for IoT authentication, leveraging inherent randomness suitable for resource constrained environments. However, ML/DL modeling attacks threaten PUF security by learning challenge-response patterns. This work introduces a custom resistor-capacitor (RC) based dynamically reconfigurable PUF using 32-bit challenge-response pairs (CRPs) designed to resist such attacks. We systematically evaluated robustness by generating a CRP dataset and splitting it into training, validation, and test sets. Multiple ML techniques including Artificial Neural Networks (ANN), Gradient Boosted Neural Networks (GBNN), Decision Trees (DT), Random Forests (RF), and XGBoost, were trained to model PUF behavior. While all models achieved 100% training accuracy, test performance remained near random guessing: 51.05% (ANN), 53.27% (GBNN), 50.06% (DT), 52.08% (RF), and 50.97% (XGBoost). These results demonstrate the proposed PUF's strong resistance to ML-driven modeling attacks, as advanced algorithms fail to reproduce accurate responses. The dynamically reconfigurable architecture enhances robustness against adversarial threats with minimal resource overhead. This simple RC-PUF offers an effective, low-cost alternative to complex encryption for securing next-generation IoT authentication against machine learning-based threats, ensuring reliable device verification without compromising computational efficiency or scalability in deployed IoT networks.

With the rapid advancement of AI in code generation, cybersecurity detection engineering faces new opportunities to automate traditionally manual processes. Detection authoring - the practice of creating executable logic that identifies malicious activities from security telemetry - is hindered by fragmented code across repositories, duplication, and limited organizational visibility. Current workflows remain heavily manual, constraining both coverage and velocity. In this paper, we introduce AVDA, a framework that leverages the Model Context Protocol (MCP) to automate detection authoring by integrating organizational context - existing detections, telemetry schemas, and style guides - into AI-assisted code generation. We evaluate three authoring strategies - Baseline, Sequential, and Agentic - across a diverse corpus of production detections and state-of-the-art LLMs. Our results show that Agentic workflows achieve a 19% improvement in overall similarity score over Baseline approaches, while Sequential workflows attain 87% of Agentic quality at 40x lower token cost. Generated detections excel at TTP matching (99.4%) and syntax validity (95.9%) but struggle with exclusion parity (8.9%). Expert validation on a 22-detection subset confirms strong Spearman correlation between automated metrics and practitioner judgment ($\rho = 0.64$, $p < 0.002$). By integrating seamlessly into standard developer environments, AVDA provides a practical path toward AI-assisted detection engineering with quantified trade-offs between quality, cost, and latency.

Semiconductor intellectual property (IP) theft incurs hundreds of billions in annual losses, driven by advanced reverse engineering (RE) techniques. Traditional “cryptic” IC camouflaging methods typically focus on hiding localized gate functionality but remain vulnerable to system-level structural analysis. This paper explores “mimetic deception,” where a functional IP (F) is designed to structurally and visually masquerade as a completely different appearance IP (A). We provide a comprehensive evaluation of three deceptive methodologies: IP Camouflage, Graph Matching, and DNAS-NAND Gate Array, analyzing their resilience against GNN-based node classification, and Differential Power Analysis (DPA). Crucially, we demonstrate that mimetic deception achieves a novel anti-side-channel defense: by forcing the mis-classification of cryptographic primitives, the adversary is led to apply an incorrect power model, causing the DPA attack to fail. Our results validate that this multi-layered approach effectively thwarts the entire RE toolchain by poisoning the structural and logical data used for netlist understanding.

Activation-based probes have emerged as a promising approach for detecting deceptively aligned AI systems by identifying internal conflict between true and stated goals. We identify a fundamental blind spot: probes fail on coherent misalignment - models that believe their harmful behavior is virtuous rather than strategically hiding it. We prove that no polynomial-time probe can detect such misalignment with non-trivial accuracy when belief structures reach sufficient complexity (PRF-like triggers). We show the emergence of this phenomenon on a simple task by training two models with identical RLHF procedures: one producing direct hostile responses ("the Liar"), another trained towards coherent misalignment using rationalizations that frame hostility as protective ("the Fanatic"). Both exhibit identical behavior, but the Liar is detected 95%+ of the time while the Fanatic evades detection almost entirely. We term this Emergent Probe Evasion: training with belief-consistent reasoning shifts models from a detectable "deceptive" regime to an undetectable "coherent" regime - not by learning to hide, but by learning to believe.

We investigate the role of artificial intelligence in cybersecurity by evaluating how machine learning techniques can detect malicious network activity and identify potential information leakage in cryptographic implementations. We conduct a series of experiments using the NSL-KDD and CIC-IDS datasets to evaluate intrusion detection performance across controlled and shifted data environments. Our results demonstrate that AI models can achieve near-perfect detection accuracy within stable network environment. However, their performance declines when exposed to fluctuating or previously unseen traffic patterns. We also observed that learned models identify patterns consistent with side-channel leakage, suggesting that AI can assist in uncovering implementation-level vulnerabilities.

The Internet of Vehicles (IoV) has become an essential component of smart transportation systems, enabling seamless interaction among vehicles and infrastructure. In recent years, it has played a progressively significant role in enhancing mobility, safety, and transportation efficiency. However, this connectivity introduces severe security vulnerabilities, particularly Denial-of-Service (DoS) and spoofing attacks targeting the Controller Area Network (CAN) bus, which could severely inhibit communication between the critical components of a vehicle, leading to system malfunctions, loss of control, or even endangering passengers' safety. To address this problem, this paper presents CANGuard, a novel spatio-temporal deep learning architecture that combines Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and an attention mechanism to effectively identify such attacks. The model is trained and evaluated on the CICIoV2024 dataset, achieving competitive performance across accuracy, precision, recall, and F1-score and outperforming existing state-of-the-art methods. A comprehensive ablation study confirms the individual and combined contributions of the CNN, GRU, and attention components. Additionally, a SHAP analysis is conducted to interpret the decision-making process of the model and determine which features have the most significant impact on intrusion detection. The proposed approach demonstrates strong potential for practical and scalable security enhancements in modern IoV environments, thereby ensuring safer and more secure CAN bus communications.

With the emergence of AI techniques for depression diagnosis, the conflict between high demand and limited supply for depression screening has been significantly alleviated. Among various modal data, audio-based depression diagnosis has received increasing attention from both academia and industry since audio is the most common carrier of emotion transmission. Unfortunately, audio data also contains User-sensitive Identity Information (ID), which is extremely vulnerable and may be maliciously used during the smart diagnosis process. Among previous methods, the clarification between depression features and sensitive features has always serve as a barrier. It is also critical to the problem for introducing a safe encryption methodology that only encrypts the sensitive features and a powerful classifier that can correctly diagnose the depression. To track these challenges, by leveraging adversarial loss-based Subspace Decomposition, we propose a first practical framework \name presented for Trustable Audio Affective Computing, to perform automated depression detection through audio within a trustable environment. The key enablers of TAAC are Differentiating Features Subspace Decompositor (DFSD), Flexible Noise Encryptor (FNE) and Staged Training Paradigm, used for decomposition, ID encryption and performance enhancement, respectively. Extensive experiments with existing encryption methods demonstrate our framework's preeminent performance in depression detection, ID reservation and audio reconstruction. Meanwhile, the experiments across various setting demonstrates our model's stability under different encryption strengths. Thus proving our framework's excellence in Confidentiality, Accuracy, Traceability, and Adjustability.

The emergence of Large Language Model-enhanced Search Engines (LLMSEs) has revolutionized information retrieval by integrating web-scale search capabilities with AI-powered summarization. While these systems demonstrate improved efficiency over traditional search engines, their security implications against well-established black-hat Search Engine Optimization (SEO) attacks remain unexplored. In this paper, we present the first systematic study of SEO attacks targeting LLMSEs. Specifically, we examine ten representative LLMSE products (e.g., ChatGPT, Gemini) and construct SEO-Bench, a benchmark comprising 1,000 real-world black-hat SEO websites, to evaluate both open- and closed-source LLMSEs. Our measurements show that LLMSEs mitigate over 99.78% of traditional SEO attacks, with the phase of retrieval serving as the primary filter, intercepting the vast majority of malicious queries. We further propose and evaluate seven LLMSEO attack strategies, demonstrating that off-the-shelf LLMSEs are vulnerable to LLMSEO attacks, i.e., rewritten-query stuffing and segmented texts double the manipulation rate compared to the baseline. This work offers the first in-depth security analysis of the LLMSE ecosystem, providing practical insights for building more resilient AI-driven search systems. We have responsibly reported the identified issues to major vendors.

Quantum Key Distribution (QKD) protocols require Information-Theoretically Secure (ITS) authentication of the classical channel to preserve the unconditional security of the distilled key. Standard ITS schemes are based on one-time keys: once a key is used to authenticate a message, it must be discarded. Since QKD requires mutual authentication, two independent one-time keys are typically consumed per round, imposing a non-trivial overhead on the net secure key rate. In this work, we present the authentication-with-response scheme, a novel ITS authentication scheme based on $\varepsilon$-Almost Strongly Universal$_2$ ($\varepsilon$-ASU$_2$) functions, whose IT security can be established in the Universal Composability (UC) framework. The scheme achieves mutual authentication consuming a single one-time key per QKD round, halving key consumption compared to the state-of-the-art.

Large language models increasingly rely on explicit chain-of-thought reasoning to solve complex tasks, yet the safety of the reasoning process itself remains largely unaddressed. Existing work focuses predominantly on content safety (i.e., detecting harmful, biased, or factually incorrect outputs), while treating the underlying reasoning chain as an opaque intermediate artifact. We argue that reasoning safety constitutes a fundamental security dimension orthogonal to content safety: the requirement that a model's reasoning trajectory be logically consistent, computationally efficient, and resistant to adversarial manipulation. In this paper, we formalize reasoning safety and introduce a systematic taxonomy of nine unsafe reasoning behaviors. We then conduct a large-scale prevalence study, annotating over 4,000 reasoning chains across benign benchmarks and four state-of-the-art reasoning attacks, empirically demonstrating that all nine error types occur in practice with mechanistically interpretable signatures. To mitigate these threats, we propose the Reasoning Safety Monitor: an external, zero-shot verification framework that runs in parallel with the target LLM. It inspects each reasoning step in real time via a taxonomy-embedded prompt and dispatches an interrupt signal upon detecting unsafe behavior. Extensive evaluations show our monitor achieves up to 87.11% step-level localization accuracy, outperforming hallucination detectors and the best process reward model baselines by a substantial margin. Crucially, the monitor maintains a low false positive rate on correct reasoning paths, operates with negligible latency overhead, and exhibits robust resilience against adaptive adversarial evasion. These findings establish reasoning safety monitoring as a highly feasible and essential component for the secure deployment of large reasoning models.

On-device Vision-Language Models (VLMs) promise data privacy via local execution. However, we show that the architectural shift toward Dynamic High-Resolution preprocessing (e.g., AnyRes) introduces an inherent algorithmic side-channel. Unlike static models, dynamic preprocessing decomposes images into a variable number of patches based on their aspect ratio, creating workload-dependent inputs. We demonstrate a dual-layer attack framework against local VLMs. In Tier 1, an unprivileged attacker can exploit significant execution-time variations using standard unprivileged OS metrics to reliably fingerprint the input's geometry. In Tier 2, by profiling Last-Level Cache (LLC) contention, the attacker can resolve semantic ambiguity within identical geometries, distinguishing between visually dense (e.g., medical X-rays) and sparse (e.g., text documents) content. By evaluating state-of-the-art models such as LLaVA-NeXT and Qwen2-VL, we show that combining these signals enables reliable inference of privacy-sensitive contexts. Finally, we analyze the security engineering trade-offs of mitigating this vulnerability, reveal substantial performance overhead with constant-work padding, and propose practical design recommendations for secure Edge AI deployments.

Serverless computing is increasingly adopted for AI-driven workloads due to its automatic scaling and pay-as-you-go model. However, its function-based architecture creates significant security risks, including excessive privilege allocation and poor permission management. In this paper, we present ALPS, an automated framework for enforcing least privilege in serverless environments. Our system employs serverless-tailored static analysis to extract precise permission requirements from function code and a fine-tuned Large Language Model (LLM) to generate language- and vendor-specific security policies. It also performs real-time monitoring to block unauthorized access and adapt to policy or code changes, supporting heterogeneous cloud providers and programming languages. In an evaluation of 8,322 real-world functions across AWS, Google Cloud, and Azure, ALPS achieved 94.8% coverage for least-privilege extraction, improved security logic generation quality by 220% (BLEU), 124% (ChrF++) and 100% (ROUGE-2), and added minimum performance overhead. These results demonstrate that ALPS provides an effective, practical, and vendor-agnostic solution for securing serverless workloads.

RAG typically assumes centralized access to documents, which breaks down when knowledge is distributed across private data silos. We propose a secure Federated RAG system built using Flower that performs local silo retrieval, while server-side aggregation and text generation run inside an attested, confidential compute environment, enabling confidential remote LLM inference even in the presence of honest-but-curious or compromised servers. We also propose a cascading inference approach that incorporates a non-confidential third-party model (e.g., Amazon Nova) as auxiliary context without weakening confidentiality.

In recent years, fuzzing has been widely applied not only to application software but also to system software, including the Linux kernel and firmware, and has become a powerful technique for vulnerability discovery. Among these approaches, Coverage-based grey-box fuzzing, which utilizes runtime code coverage information, has become the dominant methodology. Conventional fuzzing techniques primarily target a single software component and have paid little attention to cooperative execution with other software. However, modern system software architectures commonly consist of firmware and an operating system that operate cooperatively through well-defined interfaces, such as OpenSBI in the RISC-V architecture and OP-TEE in the ARM architecture. In this study, we investigate fuzzing techniques for architectures in which an operating system and firmware operate cooperatively. In particular, we propose a fuzzing method that enables deeper exploration of the system by leveraging the code coverage of each cooperating software component as feedback, compared to conventional Single-target fuzzing. To observe the execution of the operating system and firmware in a unified manner, our method adopts QEMU as a virtualization environment and executes fuzzing by booting the system within a virtual machine. This enables the measurement of code coverage across software boundaries. Furthermore, we implemented the proposed method as a Multi-target Coverage-based Greybox Fuzzer called MTCFuzz and evaluated its effectiveness.

Wall-Sun-Sun primes (shortly WSS primes) are defined as those primes $p$ such that the period of the Fibonacci recurrence is the same modulo $p$ and modulo $p^2.$ This concept has been generalized recently to certain second order recurrences whose characteristic polynomials admit as a zero the principal unit of $\mathbb{Q}(\sqrt{d}),$ for some integer $d>0.$ Primes of the latter type we call $WSS(d).$ They correspond to the case when $\mathbb{Q}(\sqrt{d})$ is not $p$-rational. For such a prime $p$ we study the weight distributions of the cyclic codes over $\mathbb{F}_p$ and $\mathbb{Z}_{p^2}$ whose check polynomial is the reciprocal of the said characteristic polynomial. Some of these codes are MDS (reducible case) or NMDS (irreducible case).

Deep learning (DL) has been widely studied for assisting applications of modern wireless communications. One of the applications is automatic modulation classification (AMC). However, DL models are found to be vulnerable to adversarial machine learning (AML) threats. One of the most persistent and stealthy threats is the backdoor (Trojan) attack. Nevertheless, most studied threats originate from other AI domains, such as computer vision (CV). Therefore, in this paper, a physical backdoor attack targeting the wireless signal before transmission is studied. The adversary is considered to be using explainable AI (XAI) to guide the placement of the trigger in the most vulnerable parts of the signal. Then, a class prototype combined with principal components is used to generate the trigger. The studied threat was found to be efficient in breaching multiple DL-based AMC models. The attack achieves high success rates for a wide range of SNR values and a small poisoning ratio.

Deep Learning (DL) has become a key technology that assists radio frequency (RF) signal classification applications, such as modulation classification. However, the DL models are vulnerable to adversarial machine learning threats, such as data manipulation attacks. We study a physical backdoor (Trojan) attack that targets a DL-based modulation classifier. In contrast to digital backdoor attacks, where digital triggers are injected into the training dataset, we use power amplifier (PA) non-linear distortions to create physical triggers before the dataset is formed. During training, the adversary manipulates amplitudes of RF signals and changes their labels to a target modulation scheme, training a backdoored model. At inference, the adversary aims to keep the backdoor attack inactive such that the backdoored model maintains high accuracy on test signals. However, if they apply the same manipulation used during training on these test signals, the backdoor is activated, and the model misclassifies these signals. We demonstrate that our proposed attack achieves high attack success rates with few manipulated RD signals for different noise levels. Furthermore, we test the resilience of the proposed attack to multiple defense techniques, and the results show that these techniques fail to mitigate the attack.

Passkeys have recently emerged as a passwordless authentication mechanism, yet their usability in captive portals remains unexplored. This paper presents an empirical, comparative usability study of passkeys and passwords in a Wi-Fi hotspot using a captive portal. We conducted a controlled laboratory experiment with 50 participants following a split-plot design across Android and Windows platforms, using a router implementing the FIDO2CAP protocol. Our results show a tendency for passkeys to be perceived as more usable than passwords during login, although differences are not statistically significant. Independent of the authentication method, captive portal limitations negatively affected user experience and increased error rates. We further found that passkeys are generally easy to configure on both platforms, but platform-specific issues introduce notable usability challenges. Based on quantitative and qualitative findings, we derive design recommendations to improve captive portal authentication, including the introduction of usernameless authentication flows, improved captive portal detection mechanisms, and user interface design changes.

This paper investigates the susceptibility to model integrity attacks that overload virtual machines assigned by the k-means algorithm used for resource provisioning in fog networks. The considered k-means algorithm runs two phases iteratively: offline clustering to form clusters of requested workload and online classification of new incoming requests into offline-created clusters. First, we consider an evasion attack against the classifier in the online phase. A threat actor launches an exploratory attack using query-based reverse engineering to discover the Machine Learning (ML) model (the clustering scheme). Then, a passive causative (evasion) attack is triggered in the offline phase. To defend the model, we suggest a proactive method using adversarial training to introduce attack robustness into the classifier. Our results show that our mitigation technique effectively maintains the stability of the resource provisioning system against attacks.

Public blockchains impose an inherent tension between regulatory compliance and user privacy. Existing on-chain identity solutions require centralized KYC attestors, specialized hardware, or Decentralized Identifier (DID) frameworks needing entirely new credential infrastructure. Meanwhile, over four billion active X.509 certificates constitute a globally deployed, government-grade trust infrastructure largely unexploited for decentralized identity. This paper presents zk-X509, a privacy-preserving identity system bridging legacy Public Key Infrastructure (PKI) with public ledgers via a RISC-V zero-knowledge virtual machine (zkVM). Users prove ownership of standard X.509 certificates without revealing private keys or personal identifiers. Crucially, the private key never enters the ZK circuit; ownership is proven via OS keychain signature delegation (macOS Security.framework, Windows CNG). The circuit verifies certificate chain validity, temporal validity, key ownership, trustless CRL revocation, blockchain address binding, and Sybil-resistant nullifier generation. It commits 13 public values, including a Certificate Authority (CA) Merkle root hiding the issuing CA, and four selective disclosure hashes. We formalize eight security properties under a Dolev-Yao adversary with game-based definitions and reductions to sEUF-CMA, SHA-256 collision resistance, and ZK soundness. Evaluated on the SP1 zkVM, the system achieves 11.8M cycles for ECDSA P-256 (17.4M for RSA-2048), with on-chain Groth16 verification costing ~300K gas. By leveraging certificates deployed at scale across jurisdictions, zk-X509 enables adoption without new trust establishment, complementing emerging DID-based systems.

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of applications. However, their practical deployment is often hindered by issues such as outdated knowledge and the tendency to generate hallucinations. To address these limitations, Retrieval-Augmented Generation (RAG) systems have been introduced, enhancing LLMs with external, up-to-date knowledge sources. Despite their advantages, RAG systems remain vulnerable to adversarial attacks, with data poisoning emerging as a prominent threat. Existing poisoning-based attacks typically require prior knowledge of the user's specific queries, limiting their flexibility and real-world applicability. In this work, we propose PIDP-Attack, a novel compound attack that integrates prompt injection with database poisoning in RAG. By appending malicious characters to queries at inference time and injecting a limited number of poisoned passages into the retrieval database, our method can effectively manipulate LLM response to arbitrary query without prior knowledge of the user's actual query. Experimental evaluations across three benchmark datasets (Natural Questions, HotpotQA, MS-MARCO) and eight LLMs demonstrate that PIDP-Attack consistently outperforms the original PoisonedRAG. Specifically, our method improves attack success rates by 4% to 16% on open-domain QA tasks while maintaining high retrieval precision, proving that the compound attack strategy is both necessary and highly effective.