arXiv AI
Agentic Security: A Systematization of Tools, Failure Modes, and Design Laws for LLM-Driven Penetration Testing
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
4d ago
PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents
PROBE is an algorithm that trains language‑model auditors to probe deployed tool‑using agents for policy violations through realistic, multi‑turn, tool‑mediated dialogue. By framing auditing as a two‑player Markov game and using a composite reward that balances violation discovery, behavioral plausibility, conversation progress, and policy diversity, PROBE outperforms zero‑shot adversaries in uncovering broader and higher‑yield policy violations. The study compares GRPO, DPO, and GFlowNet optimizations, demonstrating that multi‑turn behavioral auditing is a distinct and necessary axis of agent evaluation, complementing existing capability and safety benchmarks.
arXiv AI
Jul 7
Determinants and Limits of LLM Security-Tool Orchestration: A Study with HexStrike-AI
arXiv:2607. 02873v1 Announce Type: cross Abstract: Large language model agents driving security tool suites over the Model Context Protocol are increasingly common.
arXiv Computation and Language
Oct 8
Constrained-Action AI Remediation for SIEM/XDR via a NeMo-Guardrails Proxy
arXiv:2610.09906v1 Announce Type: cross Abstract: Security Operations Centers (SOCs) for information technology and operational technology share one incident-response problem: a flood of correlated a...
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 3
A Unified Framework for the Evaluation of LLM Agentic Capabilities
arXiv:2605. 27898v2 Announce Type: replace Abstract: As LLMs are increasingly deployed as agents, reliable assessment of their agentic capabilities has become essential.
arXiv AI
Jul 3
Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification
arXiv:2607. 01793v1 Announce Type: new Abstract: LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks.