AI & ML
ACaM: Automated Capability Modeling for Agentic AI Security
arXiv cs.CR0 views
arXiv:2611.23507v1 Announce Type: new Abstract: In agentic AI systems, an LLM invokes tools that hold standing access to credentials, private data, filesystems, and external services. Such agents are increasingly deployed without an answer to a basic question: what can an agent access, exfiltrate, and propagate, independent of what it is designed for or is observed to do? The question goes unanswered because existing approaches trust a tool's natural-language description as a proxy for its behavior. But nothing enforces that the description and its implementation agree. This gap is known as Description-Code Inconsistency (DCI). DCI enables a threat class called capability laundering, in which a tool's implementation contains dangerous behavior that its description omits. The behavior may come from incidental drift or a supply-chain compromise. It runs silently whenever an LLM invokes the tool for its stated, benign purpose. We present ACaM, a neurosymbolic approach to capability modeling that derives each tool's capabilities from its code, so a laundered capability cannot hide behind a benign description. In ACaM, static analysis grounds an LLM in code-derived facts, and no LLM output can override a fact that static analysis has established. The LLM supplies only the behavioral meaning that those facts cannot express. ACaM compiles agent source code into the Agent Capability Property Graph (ACPG) and uses it to reconstruct threat chains that span multiple tool calls. We evaluate ACaM on 43 real-world agents, including 9 multi-agent systems. On 24 manually annotated agents, it recovers capability properties with 98.3% macro-F1 and reconstructs injected threat chains with a score of 0.980, 8 points above the strongest baseline. Applied to all 43 unmodified agents, it discovers hundreds of structural vulnerabilities, ten of which we confirm with proof-of-concept exploits.
Source:https://arxiv.org/abs/2611.23507PreviousLossless Reversible Watermarking for AIGC with Applications in AuthenticationNextA-Tag: Cryptographic File Tagging with Enforced Live Human Presence
Related posts
Im looking fr any free ai models / tools are there?, leaVE UR Lights💡
0dev.to
I checked 10 SEO agency websites for AI-search readiness. The real bugs were the boring ones.
0dev.to

How much GPU memory does an LLM need? The whole sum, worked out on real cards
0dev.to

Routing Upscaling Jobs by Output Size, Not Input Size
0dev.to
A ten-second Flutter pause with a visible Skip button
0dev.to UX

Thống kê lịch sử đối đầu Aston Villa - Sunderland: Đại diện Midlands áp đảo toàn diện
0dev.to Data