POLARIS formalizes policies in FOL, constructs a Semantic Policy Graph to discover compositional violations, and generates natural-language tests, reporting higher coverage and attack success than baselines.
Liu, et al., TraceAegis: Provenance-based anomaly detection for AI agent execution traces (2025)
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Runtime Skill Audit introduces targeted runtime probing to detect malicious LLM agent skills, reporting 90% accuracy and resilience to self-evolving attacks on 100 skills versus static baselines.
AgentShield uses layered deception traps in LLM agent tool interfaces to detect indirect prompt injection compromises with 90.7-100% success on commercial models, zero false positives, and cross-lingual transfer without retraining.
Content embeddings from SBERT enable AUROC above 0.89 for attack detection in MCP tool-call sessions, with tree ensembles on pooled embeddings reaching 0.975 and outperforming GNNs when using task-stratified splits instead of random ones.
citing papers explorer
-
Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications
POLARIS formalizes policies in FOL, constructs a Semantic Policy Graph to discover compositional violations, and generates natural-language tests, reporting higher coverage and attack success than baselines.