Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation
Penetration testing traditionally evaluates whether adversaries can exploit weaknesses in software, infrastructure, configurations, or operational controls to achieve security-relevant compromise. This paradigm remains necessary for AI-enabled systems, but it is no longer sufficient. In such systems, adversaries may influence prompts, retrieved content, sensor inputs, training data, memory, tools, or human-AI interaction loops to alter system behavior without directly compromising the underlying infrastructure. This paper reframes penetration testing for AI-enabled systems as objective-driven
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 27%usestrix/strix →
“Possibly related via embedding similarity 0.60 (not asserted). Timestamp check: artifact slightly before paper (-13d).”
- PossiblePossibly related (embedding) · 26%GreyDGL/PentestGPT →
“Possibly related via embedding similarity 0.57 (not asserted). Timestamp check: artifact slightly before paper (-2d).”
- LinkedLinked via arxiv author · 85%Mohammad Allahbakhsh →
“Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation”
- LinkedLinked via arxiv author · 85%Mohammad Hassan Bahari →
“Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation”
- LinkedLinked via arxiv author · 85%Moslem Attar-Raouf →
“Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation”