Papers

Fuzz testing has become a cornerstone technique for identifying software bugs and security vulnerabilities, with broad adoption in both industry and open-source communities. Directly fuzzing a function requires fuzz drivers, which translate random fuzzer inputs into valid arguments for the target function. Given the cost and expertise required to manually develop fuzz drivers, methods exist that leverage program analysis and Large Language Models to automatically generate these drivers. However, the generated fuzz drivers frequently lead to false positive crashes, especially in functions highly structured input and complex state requirements. This problem is especially crucial in industry-scale fuzz driver generation efforts like OSS-Fuzz-en, as reporting false positive crashes to maintainers impede trust in both the system and the team. This paper presents two AI-driven strategies to reduce false positives in OSS-Fuzz-Gen, a multi-agent system for automated fuzz driver generation. First, constraint-based fuzz driver generation proactively enforces constraints on a function's inputs and state to guide driver creation. Second, context-based crash validation reactively analyzes function callers to determine whether reported crashes are feasible from program entry points. Using 1,500 benchmark functions from OSS-Fuzz, we show that these strategies reduce spurious crashes by up to 8%, cut reported crashes by more than half, and demonstrate that frontier LLMs can serve as reliable program analysis agents. Our results highlight the promise and challenges of integrating AI into large-scale fuzzing pipelines.

The growing integration of open-source software and AI-driven technologies has introduced new layers of complexity into the software supply chain, challenging existing methods for dependency management and system assurance. While Software Bills of Materials (SBOMs) have become critical for enhancing transparency and traceability, current frameworks fall short in capturing the unique characteristics of AI systems – namely, their dynamic, data-driven nature and the loosely coupled dependencies across datasets, models, and software components. These challenges are compounded by fragmented governance structures and the lack of robust tools for ensuring integrity, trust, and compliance in AI-enabled environments. In this paper, we introduce Trusted AI Bill of Materials (TAIBOM) – a novel framework extending SBOM principles to the AI domain. TAIBOM provides (i) a structured dependency model tailored for AI components, (ii) mechanisms for propagating integrity statements across heterogeneous AI pipelines, and (iii) a trust attestation process for verifying component provenance. We demonstrate how TAIBOM supports assurance, security, and compliance across AI workflows, highlighting its advantages over existing standards such as SPDX and CycloneDX. This work lays the foundation for trustworthy and verifiable AI systems through structured software transparency.

The advent of quantum computing threatens classical public-key cryptography, motivating NIST's adoption of post-quantum schemes such as those based on the Module Learning With Errors (Module-LWE) problem. We present NoMod ML-Attack, a hybrid white-box cryptanalytic method that circumvents the challenge of modeling modular reduction by treating wrap-arounds as statistical corruption and casting secret recovery as robust linear estimation. Our approach combines optimized lattice preprocessing–including reduced-vector saving and algebraic amplification–with robust estimators trained via Tukey's Biweight loss. Experiments show NoMod achieves full recovery of binary secrets for dimension $n = 350$, recovery of sparse binomial secrets for $n = 256$, and successful recovery of sparse secrets in CRYSTALS-Kyber settings with parameters $(n, k) = (128, 3)$ and $(256, 2)$. We release our implementation in an anonymous repository https://anonymous.4open.science/r/NoMod-3BD4.

Sound Event Detection (SED) systems are increasingly deployed in safety-critical applications such as industrial monitoring and audio surveillance. However, their robustness against adversarial attacks has not been well explored. Existing audio adversarial attacks targeting SED systems, which incorporate both detection and localization capabilities, often lack effectiveness due to SED's strong contextual dependencies or lack precision by focusing solely on misclassifying the target region as the target event, inadvertently affecting non-target regions. To address these challenges, we propose the Mirage and Mute Attack (M2A) framework, which is designed for targeted adversarial attacks on polyphonic SED systems. In our optimization process, we impose specific constraints on the non-target output, which we refer to as preservation loss, ensuring that our attack does not alter the model outputs for non-target region, thus achieving precise attacks. Furthermore, we introduce a novel evaluation metric Editing Precison (EP) that balances effectiveness and precision, enabling our method to simultaneously enhance both. Comprehensive experiments show that M2A achieves 94.56% and 99.11% EP on two state-of-the-art SED models, demonstrating that the framework is sufficiently effective while significantly enhancing attack precision.

As image generation models grow increasingly powerful and accessible, concerns around authenticity, ownership, and misuse of synthetic media have become critical. The ability to generate lifelike images indistinguishable from real ones introduces risks such as misinformation, deepfakes, and intellectual property violations. Traditional watermarking methods either degrade image quality, are easily removed, or require access to confidential model internals - making them unsuitable for secure and scalable deployment. We are the first to introduce ZK-WAGON, a novel system for watermarking image generation models using the Zero-Knowledge Succinct Non Interactive Argument of Knowledge (ZK-SNARKs). Our approach enables verifiable proof of origin without exposing model weights, generation prompts, or any sensitive internal information. We propose Selective Layer ZK-Circuit Creation (SL-ZKCC), a method to selectively convert key layers of an image generation model into a circuit, reducing proof generation time significantly. Generated ZK-SNARK proofs are imperceptibly embedded into a generated image via Least Significant Bit (LSB) steganography. We demonstrate this system on both GAN and Diffusion models, providing a secure, model-agnostic pipeline for trustworthy AI image generation.

Secure and interoperable integration of heterogeneous medical data remains a grand challenge in digital health. Current federated learning (FL) frameworks offer privacy-preserving model training but lack standardized mechanisms to orchestrate multi-modal data fusion across distributed and resource-constrained environments. This study introduces a novel framework that leverages the Model Context Protocol (MCP) as an interoperability layer for secure, cross-agent communication in multi-modal federated healthcare systems. The proposed architecture unifies three pillars: (i) multi-modal feature alignment for clinical imaging, electronic medical records, and wearable IoT data; (ii) secure aggregation with differential privacy to protect patient-sensitive updates; and (iii) energy-aware scheduling to mitigate dropouts in mobile clients. By employing MCP as a schema-driven interface, the framework enables adaptive orchestration of AI agents and toolchains while ensuring compliance with privacy regulations. Experimental evaluation on benchmark datasets and pilot clinical cohorts demonstrates up to 9.8% improvement in diagnostic accuracy compared with baseline FL, a 54% reduction in client dropout rates, and clinically acceptable privacy–utility trade-offs. These results highlight MCP-enabled multi-modal fusion as a scalable and trustworthy pathway toward equitable, next-generation federated health infrastructures.

We describe several families of efficiently implementable Boolean functions achieving provable trade-offs between resiliency, nonlinearity, and algebraic immunity. In particular, the following statement holds for each of the function families that we propose. Given integers $m_0\geq 0$, $x_0\geq 1$, and $a_0\geq 1$, it is possible to construct an $n$-variable function which has resiliency at least $m_0$, linear bias (which is an equivalent method of expressing nonlinearity) at most $2^{-x_0}$ and algebraic immunity at least $a_0$; further, $n$ is linear in $\max(m_0,x_0,a_0)$, and the function can be implemented using $O(n)$ 2-input gates, which is essentially optimal.

With the flourishing prosperity of generative models, manipulated facial images have become increasingly accessible, raising concerns regarding privacy infringement and societal trust. In response, proactive defense strategies embed adversarial perturbations into facial images to counter deepfake manipulation. However, existing methods often face a tradeoff between imperceptibility and defense effectiveness-strong perturbations may disrupt forgeries but degrade visual fidelity. Recent studies have attempted to address this issue by introducing additional visual loss constraints, yet often overlook the underlying gradient conflicts among losses, ultimately weakening defense performance. To bridge the gap, we propose a gradient-projection-based adversarial proactive defense (GRASP) method that effectively counters facial deepfakes while minimizing perceptual degradation. GRASP is the first approach to successfully integrate both structural similarity loss and low-frequency loss to enhance perturbation imperceptibility. By analyzing gradient conflicts between defense effectiveness loss and visual quality losses, GRASP pioneers the design of the gradient-projection mechanism to mitigate these conflicts, enabling balanced optimization that preserves image fidelity without sacrificing defensive performance. Extensive experiments validate the efficacy of GRASP, achieving a PSNR exceeding 40 dB, SSIM of 0.99, and a 100% defense success rate against facial attribute manipulations, significantly outperforming existing approaches in visual quality.

As deep learning models become widely deployed as components within larger production systems, their individual shortcomings can create system-level vulnerabilities with real-world impact. This paper studies how adversarial attacks targeting an ML component can degrade or bypass an entire production-grade malware detection system, performing a case study analysis of Gmail's pipeline where file-type identification relies on a ML model. The malware detection pipeline in use by Gmail contains a machine learning model that routes each potential malware sample to a specialized malware classifier to improve accuracy and performance. This model, called Magika, has been open sourced. By designing adversarial examples that fool Magika, we can cause the production malware service to incorrectly route malware to an unsuitable malware detector thereby increasing our chance of evading detection. Specifically, by changing just 13 bytes of a malware sample, we can successfully evade Magika in 90% of cases and thereby allow us to send malware files over Gmail. We then turn our attention to defenses, and develop an approach to mitigate the severity of these types of attacks. For our defended production model, a highly resourced adversary requires 50 bytes to achieve just a 20% attack success rate. We implement this defense, and, thanks to a collaboration with Google engineers, it has already been deployed in production for the Gmail classifier.

Computer-Use Agents (CUAs) are an increasingly deployed class of agents that take actions on GUIs to accomplish user goals. In this paper, we show that CUAs consistently exhibit Blind Goal-Directedness (BGD): a bias to pursue goals regardless of feasibility, safety, reliability, or context. We characterize three prevalent patterns of BGD: (i) lack of contextual reasoning, (ii) assumptions and decisions under ambiguity, and (iii) contradictory or infeasible goals. We develop BLIND-ACT, a benchmark of 90 tasks capturing these three patterns. Built on OSWorld, BLIND-ACT provides realistic environments and employs LLM-based judges to evaluate agent behavior, achieving 93.75% agreement with human annotations. We use BLIND-ACT to evaluate nine frontier models, including Claude Sonnet and Opus 4, Computer-Use-Preview, and GPT-5, observing high average BGD rates (80.8%) across them. We show that BGD exposes subtle risks that arise even when inputs are not directly harmful. While prompting-based interventions lower BGD levels, substantial risk persists, highlighting the need for stronger training- or inference-time interventions. Qualitative analysis reveals observed failure modes: execution-first bias (focusing on how to act over whether to act), thought-action disconnect (execution diverging from reasoning), and request-primacy (justifying actions due to user request). Identifying BGD and introducing BLIND-ACT establishes a foundation for future research on studying and mitigating this fundamental risk and ensuring safe CUA deployment.

The discourse on privacy risks in Large Language Models (LLMs) has disproportionately focused on verbatim memorization of training data, while a constellation of more immediate and scalable privacy threats remain underexplored. This position paper argues that the privacy landscape of LLM systems extends far beyond training data extraction, encompassing risks from data collection practices, inference-time context leakage, autonomous agent capabilities, and the democratization of surveillance through deep inference attacks. We present a comprehensive taxonomy of privacy risks across the LLM lifecycle – from data collection through deployment – and demonstrate through case studies how current privacy frameworks fail to address these multifaceted threats. Through a longitudinal analysis of 1,322 AI/ML privacy papers published at leading conferences over the past decade (2016–2025), we reveal that while memorization receives outsized attention in technical research, the most pressing privacy harms lie elsewhere, where current technical approaches offer little traction and viable paths forward remain unclear. We call for a fundamental shift in how the research community approaches LLM privacy, moving beyond the narrow focus of current technical solutions and embracing interdisciplinary approaches that address the sociotechnical nature of these emerging threats.

Large Language Models (LLMs) are intensively used to assist security analysts in counteracting the rapid exploitation of cyber threats, wherein LLMs offer cyber threat intelligence (CTI) to support vulnerability assessment and incident response. While recent work has shown that LLMs can support a wide range of CTI tasks such as threat analysis, vulnerability detection, and intrusion defense, significant performance gaps persist in practical deployments. In this paper, we investigate the intrinsic vulnerabilities of LLMs in CTI, focusing on challenges that arise from the nature of the threat landscape itself rather than the model architecture. Using large-scale evaluations across multiple CTI benchmarks and real-world threat reports, we introduce a novel categorization methodology that integrates stratification, autoregressive refinement, and human-in-the-loop supervision to reliably analyze failure instances. Through extensive experiments and human inspections, we reveal three fundamental vulnerabilities: spurious correlations, contradictory knowledge, and constrained generalization, that limit LLMs in effectively supporting CTI. Subsequently, we provide actionable insights for designing more robust LLM-powered CTI systems to facilitate future research.

Ball et al. recently established that prompt filtering for AI alignment faces a fundamental barrier: under standard cryptographic assumptions, no filter running significantly faster than the protected model can universally distinguish adversarial prompts from benign ones. We investigate whether this impossibility result translates to real-world vulnerabilities in deployed large language model (LLM) systems. We answer affirmatively by introducing controlled-release prompting, a practical instantiation of the theoretical framework that exploits the resource asymmetry between lightweight input filters and the main models they protect. Unlike the theoretical construction, our attack does not require model modification: it generates malicious prompts that are indecipherable by any bounded filter yet remain tractable to the target LLM. We find our attack to be successful on four major chat platforms (Google Gemini, DeepSeek Chat, xAI Grok, and Mistral Le Chat) where baseline methods fail. Additionally, we apply our attack to extract copyrighted data from Gemini. Finally, we provide a systematic evaluation of 14 open-weight prompt guard models, revealing that even reasoning-capable filters cannot reliably detect our attack without incurring prohibitive resource overhead.