Papers

Users increasingly rely on large language models (LLMs) for personal, emotionally charged, and socially sensitive conversations. However, prompts sent to cloud-hosted models can contain personally identifiable information (PII) that users do not want logged, retained, or leaked. We observe this to be especially acute when users discuss friends, coworkers, or adversaries, i.e., when they spill the tea. Enterprises face the same challenge when they want to use LLMs for internal communication and decision-making. In this whitepaper, we present Whistledown, a best-effort privacy layer that modifies prompts before they are sent to the LLM. Whistledown combines pseudonymization and $\epsilon$-local differential privacy ($\epsilon$-LDP) with transformation caching to provide best-effort privacy protection without sacrificing conversational utility. Whistledown is designed to have low compute and memory overhead, allowing it to be deployed directly on a client's device in the case of individual users. For enterprise users, Whistledown is deployed centrally within a zero-trust gateway that runs on an enterprise's trusted infrastructure. Whistledown requires no changes to the existing APIs of popular LLM providers.

The reliance of mobile GUI agents on Multimodal Large Language Models (MLLMs) introduces a severe privacy vulnerability: screenshots containing Personally Identifiable Information (PII) are often sent to untrusted, third-party routers. These routers can exploit their own MLLMs to mine this data, violating user privacy. Existing privacy perturbations fail the critical dual challenge of this scenario: protecting PII from the router's MLLM while simultaneously preserving task utility for the agent's MLLM. To address this gap, we propose the Dual-Task Adversarial Protector (DualTAP), a novel framework that, for the first time, explicitly decouples these conflicting objectives. DualTAP trains a lightweight generator using two key innovations: (i) a contrastive attention module that precisely identifies and targets only the PII-sensitive regions, and (ii) a dual-task adversarial objective that simultaneously minimizes a task-preservation loss (to maintain agent utility) and a privacy-interference loss (to suppress PII leakage). To facilitate this study, we introduce PrivScreen, a new dataset of annotated mobile screenshots designed specifically for this dual-task evaluation. Comprehensive experiments on six diverse MLLMs (e.g., GPT-5) demonstrate DualTAP's state-of-the-art protection. It reduces the average privacy leakage rate by 31.6 percentage points (a 3.0x relative improvement) while, critically, maintaining an 80.8% task success rate - a negligible drop from the 83.6% unprotected baseline. DualTAP presents the first viable solution to the privacy-utility trade-off in mobile MLLM agents.

This study proposes a novel approach to ensure the security of textual data transmission in a semantic communication system. In the proposed system, a sender transmits textual information to a receiver, while a potential eavesdropper attempts to intercept the information. At the sender side, the text is initially preprocessed, where each sentence is annotated with its corresponding topic, and subsequently extracted into a knowledge graph. To achieve the secure transmission of the knowledge graph, we propose a channel encryption scheme that integrates constellation diagonal transformation with multi-parameter weighted fractional Fourier transform (MP-WFRFT). At the receiver side, the textual data is first decrypted, and then recovered via a transformer model. Experimental results demonstrate that the proposed method reduces the probability of information compromise. The legitimate receiver achieves a Bilingual Evaluation Understudy (BLEU) score of 0.9, whereas the BLEU score of the eavesdropper remains below 0.3. Compared to the baselines, the proposed method can improve the security by up to 20%.

Backdoor attacks pose a significant threat to deep learning models by implanting hidden vulnerabilities that can be activated by malicious inputs. While numerous defenses have been proposed to mitigate these attacks, the heterogeneous landscape of evaluation methodologies hinders fair comparison between defenses. This work presents a systematic (meta-)analysis of backdoor defenses through a comprehensive literature review and empirical evaluation. We analyzed 183 backdoor defense papers published between 2018 and 2025 across major AI and security venues, examining the properties and evaluation methodologies of these defenses. Our analysis reveals significant inconsistencies in experimental setups, evaluation metrics, and threat model assumptions in the literature. Through extensive experiments involving three datasets (MNIST, CIFAR-100, ImageNet-1K), four model architectures (ResNet-18, VGG-19, ViT-B/16, DenseNet-121), 16 representative defenses, and five commonly used attacks, totaling over 3\,000 experiments, we demonstrate that defense effectiveness varies substantially across different evaluation setups. We identify critical gaps in current evaluation practices, including insufficient reporting of computational overhead and behavior under benign conditions, bias in hyperparameter selection, and incomplete experimentation. Based on our findings, we provide concrete challenges and well-motivated recommendations to standardize and improve future defense evaluations. Our work aims to equip researchers and industry practitioners with actionable insights for developing, assessing, and deploying defenses to different systems.

Jailbreak attacks can circumvent model safety guardrails and reveal critical blind spots. Prior attacks on text-to-video (T2V) models typically add adversarial perturbations to obviously unsafe prompts, which are often easy to detect and defend. In contrast, we show that benign-looking prompts containing rich, implicit cues can induce T2V models to generate semantically unsafe videos that both violate policy and preserve the original (blocked) intent. To realize this, we propose SPARK, a jailbreak framework that leverages T2V models cross-modal associative patterns via a modular prompt design. Specifically, our prompts combine three components: neutral scene anchors, which provide the surface-level scene description extracted from the blocked intent to maintain plausibility; latent auditory triggers, textual descriptions of innocuous-sounding audio events (e.g., creaking, muffled noises) that exploit learned audio-visual co-occurrence priors to bias the model toward particular unsafe visual concepts; and stylistic modulators, cinematic directives (e.g., camera framing, atmosphere) that amplify and stabilize the latent trigger's effect. We formalize attack generation as a constrained optimization over the above modular prompt space and solve it with a guided search procedure that balances stealth and effectiveness. Extensive experiments over 7 T2V models demonstrate the efficacy of our attack, achieving a +23% improvement in average attack success rate in commercial models.

Smart contracts are commonly audited through static analysis to explore vulnerabilities. However, static approaches typically produce heterogeneous findings rather than reproducible, executable proof-of-concept (PoC) test cases, leading to costly and ad hoc manual validation. Large language models (LLMs) offer a promising way to translate audit reports into PoC test cases, but face three major challenges: noisy inputs, lack of execution grounding, and missing runtime oracles. We present SmartPoC, an end-to-end approach for validating reported vulnerabilities in audit reports by generating and executing PoC test cases with automated exploitability verification. SmartPoC first extracts a focused function-level slice from each report to reduce noise, centering on the key functions referenced in a finding and augmenting them with execution-relevant neighbors. To improve executability, we wrap LLM-based PoC synthesis in a generate-repair-execute loop, combining deterministic pre-execution sanitization with feedback-driven post-execution debugging. We further use differential verification as an oracle to confirm the exploitability of generated test cases. On the SmartBugs-Vul and FORGE-Vul benchmarks, SmartPoC achieves confirmation precision of 98.32% and 98.65%, with recall of 84.17% and 85.28%, respectively. On a recent Etherscan verified-source corpus, SmartPoC confirms 64 bugs from 545 audit findings at an average cost of $0.03.

Multimodal large language models (MLLMs) have demonstrated impressive reasoning and instruction-following capabilities, yet their expanded modality space introduces new compositional safety risks that emerge from complex text-image interactions. Such cross-modal couplings can produce unsafe semantics even when individual inputs are benign, exposing the fragile safety awareness of current MLLMs. While recent works enhance safety by guiding models to reason about potential risks, unregulated reasoning traces may compromise alignment; although Group Relative Policy Optimization (GRPO) offers self-rewarded refinement without human supervision, it lacks verifiable signals for reasoning safety. To address this, we propose SafeGRPO a self-rewarded multimodal safety alignment framework that integrates rule-governed reward construction into GRPO, enabling interpretable and verifiable optimization of reasoning safety. Built upon the constructed SafeTag-VL-3K dataset with explicit visual, textual, and combined safety tags, SafeGRPO performs step-guided safety thinking to enforce structured reasoning and behavior alignment, substantially improving multimodal safety awareness, compositional robustness, and reasoning stability across diverse benchmarks without sacrificing general capabilities.

The first contribution of the paper is to put forward an abstract definition of the Grain family of stream ciphers which formalises the different components that are required to specify a particular member of the family. Our second contribution is to provide new and strengthened definitions of the components. These include definining new classes of nonlinear Boolean functions, improved definition of the state update function during initialisation, choice of the tap positions, and the possibility of the linear feedback shift register being smaller than the nonlinear feedback shift register. The third contribution of the paper is to put forward seven concrete proposals of stream ciphers by suitably instantiating the abstract family, one at the 80-bit security level, and two each at the 128-bit, 192-bit, and the 256-bit security levels. At the 80-bit security level, compared to the well known Grain~v1, the new proposal uses Boolean functions with improved cryptographic properties and an overall lower gate count. At the 128-bit level, compared to ISO/IEC standard Grain-128a, the new proposals use Boolean functions with improved cryptographic properties; one of the proposals require a few extra gates, while the other has an overall lower gate count. At the 192-bit, and the 256-bit security levels, there are no proposals in the literature with smaller gate counts.

Decentralized finance (DeFi) is experiencing rapid expansion. However, prevalent code reuse and limited open-source contributions have introduced significant challenges to the blockchain ecosystem, including plagiarism and the propagation of vulnerable code. Consequently, an effective and accurate similarity detection method for EVM bytecode is urgently needed to identify similar contracts. Traditional binary similarity detection methods are typically based on instruction stream or control flow graph (CFG), which have limitations on EVM bytecode due to specific features like low-level EVM bytecode and heavily-reused basic blocks. Moreover, the highly-diverse Solidity Compiler (Solc) versions further complicate accurate similarity detection. Motivated by these challenges, we propose a novel EVM bytecode representation called Stable-Semantic Graph (SSG), which captures relationships between 'stable instructions' (special instructions identified by our study). Moreover, we implement a prototype, Esim, which embeds SSG into matrices for similarity detection using a heterogeneous graph neural network. Esim demonstrates high accuracy in SSG construction, achieving F1-scores of 100% for control flow and 95.16% for data flow, and its similarity detection performance reaches 96.3% AUC, surpassing traditional approaches. Our large-scale study, analyzing 2,675,573 smart contracts on six EVM-compatible chains over a one-year period, also demonstrates that Esim outperforms the SOTA tool Etherscan in vulnerability search.

Traffic Sign Recognition (TSR) systems play a critical role in Autonomous Driving (AD) systems, enabling real-time detection of road signs, such as STOP and speed limit signs. While these systems are increasingly integrated into commercial vehicles, recent research has exposed their vulnerability to physical-world adversarial appearance attacks. In such attacks, carefully crafted visual patterns are misinterpreted by TSR models as legitimate traffic signs, while remaining inconspicuous or benign to human observers. However, existing adversarial appearance attacks suffer from notable limitations. Pixel-level perturbation-based methods often lack stealthiness and tend to overfit to specific surrogate models, resulting in poor transferability to real-world TSR systems. On the other hand, text-to-image (T2I) diffusion model-based approaches demonstrate limited effectiveness and poor generalization to out-of-distribution sign types. In this paper, we present DiffSign, a novel T2I-based appearance attack framework designed to generate physically robust, highly effective, transferable, practical, and stealthy appearance attacks against TSR systems. To overcome the limitations of prior approaches, we propose a carefully designed attack pipeline that integrates CLIP-based loss and masked prompts to improve attack focus and controllability. We also propose two novel style customization methods to guide visual appearance and improve out-of-domain traffic sign attack generalization and attack stealthiness. We conduct extensive evaluations of DiffSign under varied real-world conditions, including different distances, angles, light conditions, and sign categories. Our method achieves an average physical-world attack success rate of 83.3%, leveraging DiffSign's high effectiveness in attack transferability.

In federated learning, multiple parties can cooperate to train the model without directly exchanging their own private data, but the gradient leakage problem still threatens the privacy security and model integrity. Although the existing scheme uses threshold cryptography to mitigate the inference attack, it can not guarantee the verifiability of the aggregation results, making the system vulnerable to the threat of poisoning attack. We construct a partial decryption verifiable threshold multi client function encryption scheme, and apply it to Federated learning to implement the federated learning verifiable threshold security aggregation protocol (VTSAFL). VTSAFL empowers clients to verify aggregation results, concurrently minimizing both computational and communication overhead. The size of the functional key and partial decryption results of the scheme are constant, which provides efficiency guarantee for large-scale deployment. The experimental results on MNIST dataset show that vtsafl can achieve the same accuracy as the existing scheme, while reducing the total training time by more than 40%, and reducing the communication overhead by up to 50%. This efficiency is critical for overcoming the resource constraints inherent in Internet of Things (IoT) devices.

Backdoor attacks pose a serious threat to the security of large language models (LLMs), causing them to exhibit anomalous behavior under specific trigger conditions. The design of backdoor triggers has evolved from fixed triggers to dynamic or implicit triggers. This increased flexibility in trigger design makes it challenging for defenders to identify their specific forms accurately. Most existing backdoor defense methods are limited to specific types of triggers or rely on an additional clean model for support. To address this issue, we propose a backdoor detection method based on attention similarity, enabling backdoor detection without prior knowledge of the trigger. Our study reveals that models subjected to backdoor attacks exhibit unusually high similarity among attention heads when exposed to triggers. Based on this observation, we propose an attention safety alignment approach combined with head-wise fine-tuning to rectify potentially contaminated attention heads, thereby effectively mitigating the impact of backdoor attacks. Extensive experimental results demonstrate that our method significantly reduces the success rate of backdoor attacks while preserving the model's performance on downstream tasks.

Large language models (LLMs) increasingly operate in multi-agent and safety-critical settings, raising open questions about how their vulnerabilities scale when models interact adversarially. This study examines whether larger models can systematically jailbreak smaller ones - eliciting harmful or restricted behavior despite alignment safeguards. Using standardized adversarial tasks from JailbreakBench, we simulate over 6,000 multi-turn attacker-target exchanges across major LLM families and scales (0.6B-120B parameters), measuring both harm score and refusal behavior as indicators of adversarial potency and alignment integrity. Each interaction is evaluated through aggregated harm and refusal scores assigned by three independent LLM judges, providing a consistent, model-based measure of adversarial outcomes. Aggregating results across prompts, we find a strong and statistically significant correlation between mean harm and the logarithm of the attacker-to-target size ratio (Pearson r = 0.51, p < 0.001; Spearman rho = 0.52, p < 0.001), indicating that relative model size correlates with the likelihood and severity of harmful completions. Mean harm score variance is higher across attackers (0.18) than across targets (0.10), suggesting that attacker-side behavioral diversity contributes more to adversarial outcomes than target susceptibility. Attacker refusal frequency is strongly and negatively correlated with harm (rho = -0.93, p < 0.001), showing that attacker-side alignment mitigates harmful responses. These findings reveal that size asymmetry influences robustness and provide exploratory evidence for adversarial scaling patterns, motivating more controlled investigations into inter-model alignment and safety.

Human-centered threat modeling (HCTM) is an emerging area within security and privacy research that focuses on how people define and navigate threats in various social, cultural, and technological contexts. While researchers increasingly approach threat modeling from a human-centered perspective, little is known about how they prepare for and engage with HCTM in practice. In this work, we conduct 23 semi-structured interviews with researchers to examine the state of HCTM, including how researchers design studies, elicit threats, and navigate values, constraints, and long-term goals. We find that HCTM is not a prescriptive process but a set of evolving practices shaped by relationships with participants, disciplinary backgrounds, and institutional structures. Researchers approach threat modeling through sustained groundwork and participant-centered inquiry, guided by values such as care, justice, and autonomy. They also face challenges including emotional strain, ethical dilemmas, and structural barriers that complicate efforts to translate findings into real-world impact. We conclude by identifying opportunities to advance HCTM through shared infrastructure, broader recognition of diverse contributions, and stronger mechanisms for translating findings into policy, design, and societal change.

Personal communication using technical means is protected by telecommunications secrecy. Any interference with this fundamental right requires a legal basis, which has existed for many years for traditional communication services in the form of telecommunications surveillance (TKÜ, {\S} 100a StPO) and appears to be widely accepted by society. The basis for the implementation of TKÜ is the obligation of telecommunications providers to provide interception interfaces. However, the technical implementation of telecommunications has changed significantly as a result of the Internet. Messenger services and Voice over IP telephony are increasingly competing with traditional telephone services. The use of strong end-to-end encryption made possible by this technology is increasingly posing problems for law enforcement agencies, as only cryptographically encrypted content is accessible via the interception interfaces provided to date. Against the backdrop of current discussions on socalled “chat control” and its limited social acceptance, this article addresses the question of whether and, if so, how the cooperation obligations of the technical actors involved can be sensibly regulated in the case of encrypted communication.

The deployment of robust malware detection systems in big data environments requires careful consideration of both security effectiveness and computational efficiency. While recent advances in adversarial defenses have demonstrated strong robustness improvements, they often introduce computational overhead ranging from 4x to 22x, which presents significant challenges for production systems processing millions of samples daily. In this work, we propose a novel framework that combines Trust-Raw Override (TRO) with Confidence-Adaptive Bit-Depth Reduction (CABDR) to explicitly optimize the trade-off between adversarial robustness and computational efficiency. Our approach leverages adaptive confidence-based mechanisms to selectively apply defensive measures, achieving 1.76x computational overhead - a 2.3x improvement over state-of-the-art smoothing defenses. Through comprehensive evaluation on the EMBER v2 dataset comprising 800K samples, we demonstrate that our framework maintains 91 percent clean accuracy while reducing attack success rates to 31-37 percent across multiple attack types, with particularly strong performance against optimization-based attacks such as C and W (48.8 percent reduction). The framework achieves throughput of up to 1.26 million samples per second (measured on pre-extracted EMBER features with no runtime feature extraction), validated across 72 production configurations with statistical significance (5 independent runs, 95 percent confidence intervals, p less than 0.01). Our results suggest that practical adversarial robustness in production environments requires explicit optimization of the efficiency-robustness trade-off, providing a viable path for organizations to deploy robust defenses without prohibitive infrastructure costs.

Current Large Language Model alignment research mostly focuses on improving model robustness against adversarial attacks and misbehavior by training on examples and prompting. Research has shown that LLM jailbreak probability increases with the size of the user input or conversation length. There is a lack of appropriate research into means of strengthening alignment which also scale with user input length. We propose interruptions as a possible solution to this problem. Interruptions are control sentences added to the user input approximately every x tokens for some arbitrary x. We suggest that this can be generalized to the Chain-of-Thought process to prevent scheming.

High-Altitude Platform Stations (HAPS) are emerging stratospheric nodes within non-terrestrial networks. We provide a structured overview of HAPS subsystems and principal communication links, map cybersecurity and privacy exposure across communication, control, and power subsystems, and propose a stratosphere-aware threat taxonomy. We then discuss defenses feasible under HAPS constraints including encryption and authentication, frequency agility, directional and beam-steered antennas, intrusion detection, secure boot, and software and supply-chain assurance-while highlighting how they align with emerging regulatory and standards guidance. Finally, we report a simulation-based case study using OMNeT++/INET to characterize distributed-denial-of-service (DDoS) impact on service and control-plane availability, and summarize regulatory and standardization considerations relevant to deployment. We conclude with concrete future research directions. The study is simulation-grounded and intended to inform engineering trade-offs for real-world HAPS deployments rather than serve as an on-air validation.

The Key Value(KV) cache is an important component for efficient inference in autoregressive Large Language Models (LLMs), but its role as a representation of the model's internal state makes it a potential target for integrity attacks. This paper introduces "History Swapping," a novel block-level attack that manipulates the KV cache to steer model generation without altering the user-facing prompt. The attack involves overwriting a contiguous segment of the active generation's cache with a precomputed cache from a different topic. We empirically evaluate this method across 324 configurations on the Qwen 3 family of models, analyzing the impact of timing, magnitude, and layer depth of the cache overwrite. Our findings reveal that only full-layer overwrites can successfully hijack the conversation's topic, leading to three distinct behaviors: immediate and persistent topic shift, partial recovery, or a delayed hijack. Furthermore, we observe that high-level structural plans are encoded early in the generation process and local discourse structure is maintained by the final layers of the model. This work demonstrates that the KV cache is a significant vector for security analysis, as it encodes not just context but also topic trajectory and structural planning, making it a powerful interface for manipulating model behavior.

The performance of Machine Learning (ML) and Deep Learning (DL)-based Intrusion Detection and Prevention Systems (IDS/IPS) is critically dependent on the relevance and quality of the datasets used for training and evaluation. However, current AI model evaluation practices for developing IDS/IPS focus predominantly on accuracy metrics, often overlooking whether datasets represent industry-specific threats. To address this gap, we introduce a novel multi-dimensional framework that integrates the MITRE ATT&CK knowledge base for threat intelligence and employs five complementary metrics that together provide a comprehensive assessment of dataset suitability. Methodologically, this framework combines threat intelligence, natural language processing, and quantitative analysis to assess the suitability of datasets for specific industry contexts. Applying this framework to nine publicly available IDS/IPS datasets reveals significant gaps in threat coverage, particularly in the healthcare, energy, and financial sectors. In particular, recent datasets (e.g., CIC-IoMT, CIC-UNSW-NB15) align better with sector-specific threats, whereas others, like CICIoV-24, underperform despite their recency. Our findings provide a standardized, interpretable approach for selecting datasets aligned with sector-specific operational requirements, ultimately enhancing the real-world effectiveness of AI-driven IDS/IPS deployments. The efficiency and practicality of the framework are validated through deployment in a real-world case study, underscoring its capacity to inform dataset selection and enhance the effectiveness of AI-driven IDS/IPS in operational environments.

Fingerprint recognition systems are widely deployed for authentication and forensic applications, but the security of stored fingerprint data remains a critical vulnerability. While many systems avoid storing raw fingerprint images in favor of minutiae-based templates, recent research shows that these templates can be reverse-engineered to reconstruct realistic fingerprint images, enabling physical spoofing attacks that compromise user identities with no means of remediation. We present ProxyPrints, the first practical defense that brings cancellable biometrics to existing fingerprint recognition systems without requiring modifications to proprietary matching software. ProxyPrints acts as a transparent middleware layer between the fingerprint scanner and the matching algorithm, transforming each scanned fingerprint into a consistent, unlinkable alias. This transformation allows biometric identities to be revoked and replaced in the event of a breach, without affecting authentication accuracy. Additionally, ProxyPrints provides organizations with breach detection capabilities by enabling the identification of out-of-band spoofing attempts involving compromised aliases. We evaluate ProxyPrints on standard benchmark datasets and commercial fingerprint recognition systems, demonstrating that it preserves matching performance while offering strong security and revocability. Our open-source implementation includes tools for alias generation and deployment in real-world pipelines, making ProxyPrints a drop-in, scalable solution for fingerprint data protection.

Automated red teaming frameworks for Large Language Models (LLMs) have become increasingly sophisticated, yet many still formulate attack optimization primarily in the prompt space. In other words, these methods mainly search for better attack wording or better strategy choices, but they do not search over executable code. By moving the search into code space, we can optimize not only the final attack prompt, but also the procedure that generates it, including execution flow, reusable logic, branching, and failure-driven repair. To overcome this gap, we introduce EvoSynth, an autonomous multi-agent framework that shifts the optimization space from prompts to executable code. Instead of refining prompts directly, EvoSynth employs a multi-agent system to autonomously engineer, evolve, and execute code-based attack algorithms. Crucially, it features a code-level self-correction loop, allowing it to iteratively rewrite the code-based algorithm in response to target-model feedback and failed attempts. Through extensive experiments, we demonstrate that EvoSynth achieves an 85.5% Attack Success Rate (ASR) against highly robust models like Claude-Sonnet-4.5 and a 95.9% average ASR across evaluated targets, while generating attacks that are significantly more diverse than those from existing methods. We release our framework to facilitate future research on evolutionary synthesis in executable code space.

Intentional threats are a major risk factor related to vulnerabilities in critical infrastructure assets, and an accurate risk assessment is necessary to analyze threats, assess vulnerabilities, and evaluate potential impacts on assets and systems. This research proposes a methodology that can be added as an additional phase in the risk assessment process. The method introduces an extra analytical parameter concerning offensive tool characteristics, improving the understanding of intentional threats. The methodology is presented using clear and accessible language suitable for a broad audience. It is based on an approach described as an "offensive tool determination strategy," summarized by the acronym R.I.D.D.L.E.+C, which refers to the variables used in the analysis: resistance, intrusion timing, damage, disruption timing, latency, efficiency, and cost. These variables are evaluated using open-source intelligence. Each variable is assigned a specific range of values according to its potential impact on the targeted asset. A matrix is then provided for practical application, which can reveal unexpected vulnerabilities and offer a more granular framework for decision-making and security planning.

Assurance for artificial intelligence (AI) systems remains fragmented across software supply-chain security, adversarial machine learning, and governance documentation. Existing transparency mechanisms - including Model Cards, Datasheets, and Software Bills of Materials (SBOMs) - advance provenance reporting but rarely provide verifiable, machine-readable evidence of model security. This paper introduces the AI Risk Scanning (AIRS) Framework, a threat-model-based, evidence-generating framework designed to operationalize AI assurance. The AIRS Framework evolved through three progressive pilot studies - Smurf (AIBOM schema design), OPAL (operational validation), and Pilot C (AIRS) - that reframed AI documentation from descriptive disclosure toward measurable, evidence-bound verification. The framework aligns its assurance fields to the MITRE ATLAS adversarial ML taxonomy and automatically produces structured artifacts capturing model integrity, packaging and serialization safety, structural adapters, and runtime behaviors. Currently, the AIRS Framework is scoped to provide model-level assurances for LLMs, but it could be expanded to include other modalities and cover system-level threats (e.g. application-layer abuses, tool-calling). A proof-of-concept on a quantized GPT-OSS-20B model demonstrates enforcement of safe loader policies, per-shard hash verification, and contamination and backdoor probes executed under controlled runtime conditions. Comparative analysis with SBOM standards of SPDX 3.0 and CycloneDX 1.6 reveals alignment on identity and evaluation metadata, but identifies critical gaps in representing AI-specific assurance fields. The AIRS Framework thus extends SBOM practice to the AI domain by coupling threat modeling with automated, auditable evidence generation, providing a principled foundation for standardized, trustworthy, and machine-verifiable AI risk documentation.

Federated learning (FL) enables multiple clients to collaboratively train a shared global model while preserving the privacy of their local data. Within this paradigm, the intellectual property rights (IPR) of client models are critical assets that must be protected. In practice, the central server responsible for maintaining the global model may maliciously manipulate the global model to erase client contributions or falsely claim sole ownership, thereby infringing on clients' IPR. Watermarking has emerged as a promising technique for asserting model ownership and protecting intellectual property. However, existing FL watermarking approaches remain limited, suffering from potential watermark collisions among clients, insufficient watermark security, and non-intuitive verification mechanisms. In this paper, we propose FLClear, a novel framework that simultaneously achieves collision-free watermark aggregation, enhanced watermark security, and visually interpretable ownership verification. Specifically, FLClear introduces a transposed model jointly optimized with contrastive learning to integrate the watermarking and main task objectives. During verification, the watermark is reconstructed from the transposed model and evaluated through both visual inspection and structural similarity metrics, enabling intuitive and quantitative ownership verification. Comprehensive experiments conducted over various datasets, aggregation schemes, and attack scenarios demonstrate the effectiveness of FLClear and confirm that it consistently outperforms state-of-the-art FL watermarking methods.

Boolean functions with strong cryptographic properties, such as high nonlinearity and algebraic degree, are important for the security of stream and block ciphers. These functions can be designed using algebraic constructions or metaheuristics. This paper examines the use of Evolutionary Algorithms (EAs) to evolve homogeneous bent Boolean functions, that is, functions whose algebraic normal form contains only monomials of the same degree and that are maximally nonlinear. We introduce the notion of density of homogeneous bent functions, facilitating the algorithmic design that results in finding quadratic and cubic bent functions in different numbers of variables.

The security of autonomous vehicle networks is facing major challenges, owing to the complexity of sensor integration, real-time performance demands, and distributed communication protocols that expose vast attack surfaces around both individual and network-wide safety. Existing security schemes are unable to provide sub-10 ms (milliseconds) anomaly detection and distributed coordination of large-scale networks of vehicles within an acceptable safety/privacy framework. This paper introduces a three-tier hybrid security architecture HAVEN (Hierarchical Autonomous Vehicle Enhanced Network), which decouples real-time local threat detection and distributed coordination operations. It incorporates a light ensemble anomaly detection model on the edge (first layer), Byzantine-fault-tolerant federated learning to aggregate threat intelligence at a regional scale (middle layer), and selected blockchain mechanisms (top layer) to ensure critical security coordination. Extensive experimentation is done on a real-world autonomous driving dataset. Large-scale simulations with the number of vehicles ranging between 100 and 1000 and different attack types, such as sensor spoofing, jamming, and adversarial model poisoning, are conducted to test the scalability and resiliency of HAVEN. Experimental findings show sub-10 ms detection latency with an accuracy of 94% and F1-score of 92% across multimodal sensor data, Byzantine fault tolerance validated with 20% compromised nodes, and a reduced blockchain storage overhead, guaranteeing sufficient differential privacy. The proposed framework overcomes the important trade-off between real-time safety obligation and distributed security coordination with novel three-tiered processing. The scalable architecture of HAVEN is shown to provide great improvement in detection accuracy as well as network resilience over other methods.

Web Application Firewalls are crucial for protecting web applications against a wide range of cyber threats. Traditional Web Application Firewalls often struggle to effectively distinguish between malicious and legitimate traffic, leading to limited efficacy in threat detection. To overcome these limitations, this paper proposes an Adaptive Dual-Layer WAF employing a two-layered Machine Learning model designed to enhance the accuracy of anomaly and threat detection. The first layer employs a Decision Tree (DT) algorithm to detect anomalies by identifying traffic deviations from established normal patterns. The second layer employs Support Vector Machine to classify these anomalies as either threat anomalies or benign anomalies. Our Adaptive Dual Layer WAF incorporates comprehensive data pre-processing and feature engineering techniques and has been thoroughly evaluated using five large benchmark datasets. Evaluation using these datasets shows that ADL WAF achieves a detection accuracy of 99.88% and a precision of 100%, significantly enhancing anomaly detection and reducing false positives. These findings suggest that integrating machine learning techniques into WAFs can substantially improve web application security by providing more accurate and efficient threat detection.

Smart contracts, the stateful programs running on blockchains, often rely on reports. Publishers are paid to publish these reports on the blockchain. Designing protocols that incentivize timely reporting is the prevalent reporting problem. But existing solutions face a security-performance trade-off: Relying on a small set of trusted publishers introduces centralization risks, while allowing open publication results in an excessive number of reports on the blockchain. We identify the root cause of this trade-off to be the standard symmetric reward design, which treats all reports equally. We prove that no symmetric-reward mechanism can overcome the trade-off. We present Personal Random Rewards for Reporting (Prrr), a protocol that assigns random heterogeneous values to reports. We call this novel mechanism-design concept Ex-Ante Synthetic Asymmetry. To the best of our knowledge, Prrr is the first game-theoretic mechanism (in any context) that deliberately forms participant asymmetry. Prrr employs a second-price-style settlement to allocate rewards, ensuring incentive compatibility and achieving both security and efficiency. Following the protocol constitutes a Subgame-Perfect Nash Equilibrium, robust against collusion and Sybil attacks. Prrr is applicable to numerous smart contracts that rely on timely reports.

Existing linguistic steganography methods primarily rely on content transformations to conceal secret messages. However, they often cause subtle yet looking-innocent deviations between normal and stego texts, posing potential security risks in real-world applications. To address this challenge, we propose a content-preserving linguistic steganography paradigm for perfectly secure covert communication without modifying the cover text. Based on this paradigm, we introduce CLstega (Content-preserving Linguistic steganography), a novel method that embeds secret messages through controllable distribution transformation. CLstega first applies an augmented masking strategy to locate and mask embedding positions, where MLM(masked language model)-predicted probability distributions are easily adjustable for transformation. Subsequently, a dynamic distribution steganographic coding strategy is designed to encode secret messages by deriving target distributions from the original probability distributions. To achieve this transformation, CLstega elaborately selects target words for embedding positions as labels to construct a masked sentence dataset, which is used to fine-tune the original MLM, producing a target MLM capable of directly extracting secret messages from the cover text. This approach ensures perfect security of secret messages while fully preserving the integrity of the original cover text. Experimental results show that CLstega can achieve a 100% extraction success rate, and outperforms existing methods in security, effectively balancing embedding capacity and security.