arXiv AI
Jul 1
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
arXiv:2606. 30755v1 Announce Type: cross Abstract: Claw-like AI agents (e.
HardEval: An Execution-Verified Benchmark for AI-Driven Security Hardening and Compliance Remediation
HardEval is an execution‑verified benchmark that tests language‑model‑assisted security hardening on a live Red Hat Enterprise Linux 8 system. It uses STIG controls that fail on an unhardened baseline, and models generate Bash scripts that are run on a virtual machine and graded by OpenSCAP/OVAL compliance checks. The benchmark reveals significant differences in model performance across security domains and highlights failures where code appears plausible but does not meet the exact compliance condition.
Related stories
arXiv AI
Oct 15
Scalable Weak-to-Strong Verifier Hardening for Agent Environments
arXiv:2610.15924v1 Announce Type: cross Abstract: Agent environments are essential for large language model (LLM) development. They use programmatic verifiers to turn complex outcomes into rewards. V...
arXiv AI
Sep 12
Beyond Static Guarantees: Measuring the Static-Pass Dynamic-Fail Gap in Security-Sensitive and LLM-Generated Python Code
The paper introduces the Static‑Pass Dynamic‑Fail (SPDF) phenomenon, showing that static analysis can miss vulnerabilities that are exploitable at runtime. Using a three‑stage pipeline—static scanning, LLM‑driven CWE reasoning, and autonomous exploit verification—it evaluated 1,355 Python samples and found that 14.53% of samples that passed static checks were actually exploitable. The study highlights that static‑analysis success and runtime security are distinct assurance layers, especially for AI‑generated and security‑sensitive code.
arXiv AI
Jun 17
Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks
arXiv:2510. 01359v2 Announce Type: replace-cross Abstract: Code-capable large language model (LLM) agents are embedded in software engineering workflows where they can read, write, and execute code, raising "jailbreak" stakes beyond text-only settings.
arXiv Machine Learning
Jul 21
SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?
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 AI
Jul 22
Data Leakage Prevention in Agentic Applications via Preemptive Hardening
arXiv:2607. 18847v1 Announce Type: cross Abstract: Agentic systems integrate LLM driven planning with interfaces to external tools, making data leakage and tool misuse feasible via instruction/data boundary failures and prompt injection attacks.
arXiv AI
Oct 2
KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards
KaliBench is a fine‑grained benchmark that evaluates large language models’ ability to translate natural‑language queries into executable command‑line instructions for Kali Linux. It contains 8,504 query–command pairs covering 1,642 tools across 23 capability dimensions and 5 security phases, and uses a deterministic, alias‑aware evaluation pipeline with multi‑stage verification (LLM validation, sandboxed execution, and human refinement). The benchmark also supports runtime‑free verifiable rewards, enabling training improvements that bring smaller models close to the performance of a 685B MoE model.
arXiv AI
Jun 9
Automated Framework to Evaluate and Harden LLM System Instructions against Encoding Attacks
arXiv:2604. 01039v2 Announce Type: replace-cross Abstract: System Instructions in Large Language Models (LLMs) are commonly used to enforce safety policies, define agent behavior, and protect sensitive operational context in agentic AI applications.
arXiv AI
Oct 5
EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents
arXiv:2610.03153v1 Announce Type: cross Abstract: Workspace agents combine large language models with execution harnesses to perform stateful, multi-step tasks that access or modify external resource...
arXiv AI
Jul 21
STAC: When Innocent Tools Form Dangerous Chains for LLM Agents
arXiv:2509. 25624v3 Announce Type: replace-cross Abstract: As LLMs advance into autonomous agents with tool-use capabilities, they introduce security challenges that extend beyond traditional content-based LLM safety concerns.
arXiv AI
Jul 20
Jailbreak Foundry: From Papers to Runnable Attacks for Reproducible Benchmarking
arXiv:2602. 24009v4 Announce Type: replace-cross Abstract: Jailbreak techniques for large language models (LLMs) evolve faster than benchmarks, making robustness estimates stale and difficult to compare across papers due to drift in datasets, harnesses, and judging protocols.
arXiv Computation and Language
1d ago
Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness
arXiv:2610.37657v1 Announce Type: cross Abstract: We introduce Heads of Security (HoS), a prompt injection defense that enforces instruction-data separation via a small set of learned per-head attent...