Tag
This paper proposes a new security paradigm for AI agents using a Proof-Constrained Action (ePCA) framework with neural symbolic isolation, achieving zero attack success rate in empirical evaluations.
The paper introduces Chimera Training, a method for logical anomaly detection that uses counterfactual construction at the feature level to train neural rule evaluators without requiring real anomalous images, improving rule-level anomaly detection performance on benchmarks like CLEVRER, OpenImages, and VidOR.