CESBench is a new benchmark for evaluating large language models on cryptographic engineering security for IoT devices, comprising 380 expert‑written items across six sub‑domains such as side‑channel, fault injection, and implementation. The benchmark includes four task types—multiple‑choice, judgment, scenario, and code—each designed to test different competences, with automatic scoring for the first two and LLM‑based judging for the latter two. Evaluation of 11 open‑weight and proprietary LLMs shows strong performance on multiple‑choice and code tasks but weaker results on judgment and scenario tasks, highlighting gaps in justifying security verdicts.
arXiv:2512. 18542v3 Announce Type: replace-cross Abstract: AI coding assistants produce vulnerable code in 45\% of security-relevant scenarios~\cite{veracode2025}, yet no public training dataset teaches both traditional web security and AI/ML-specific defenses in a format suitable for instruction tuning.
arXiv:2608. 11492v1 Announce Type: cross Abstract: IoT firmware vulnerability detection remains challenging due to heterogeneous firmware ecosystems, resource-constrained platforms, and limitations in existing benchmarks.
arXiv:2604. 03750v2 Announce Type: replace-cross Abstract: Reverse engineering (RE) is central to software security, particularly for cryptographic programs that handle sensitive data and are highly prone to vulnerabilities.
arXiv:2605. 26548v2 Announce Type: replace-cross Abstract: Finding a real vulnerability in complicated systems is a challenging, long-horizon task that demands reasoning across an entire codebase to produce a working proof-of-concept (PoC).
arXiv:2510. 14113v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are transforming everyday applications, yet deployment in cybersecurity lags due to a lack of high-quality, domain-specific models and training datasets.
arXiv:2607. 20712v1 Announce Type: cross Abstract: Security protocol verification relies on formal tools such as ProVerif and OFMC.
The paper examines how the scores of cybersecurity large language model (LLM) benchmarks vary depending on the evaluation pipeline used. By auditing eight benchmarks across ten different LLMs, the authors uncover 15 systematic failure modes and demonstrate that a single pipeline choice can shift a model’s score by over 80 percentage points, significantly altering rankings. They also show that even semantically similar tasks can produce different model rankings due to incompatible evaluation conventions, and that standardizing pipelines can move most models by at least three ranks on at least one benchmark.
CS-Guard is a new benchmark that systematically evaluates guardrails for code generation security, covering 1,000 malware-generation prompts, 7 jailbreak attacks, and a novel fictional scenario attack (FSA) for text-to-code generation, as well as 331 code prompts for code-to-code generation. The study empirically tests nine guardrails across seven large language models, finding that many guardrails fail to prevent malicious code generation, with attack success rates reaching about 50% for text-to-code and up to nearly 100% for code-to-code and FSA scenarios. CS-Guard introduces a modular three-layer guardrail taxonomy and releases its benchmark and data to support future research.
arXiv:2606. 15899v1 Announce Type: cross Abstract: Open-source LLM agent ecosystems are growing rapidly, yet the security of community-contributed skills - modular tool definitions that extend agent capabilities - remains largely unvetted.
arXiv:2510. 15476v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used as interfaces to information, code, and real-world services, making prompt-level security failures a practical concern.
arXiv:2609.33401v2 Announce Type: replace-cross Abstract: Model-based judges support agent security by detecting prompt injections, assessing interaction risks, and screening harmful requests. System...
The paper proposes using lightweight, calibrated System One decision models—specifically JEV and Laya—to improve autonomous penetration-testing harnesses that rely on large language models (LLMs). It defines four key decision points (finding adjudication, severity recalibration, agent pruning, and confirmation loops) and presents a NeuroSploit case study showing differences in severity distribution, runtime, and grading when using TypeSafe System One. The authors review existing System One specifications, discuss various RL-based training approaches, and introduce Rave, a domain‑adapted model with a proposed training and evaluation framework.