
purple-team-exercise-framework
Purple Team Exercise Framework

Purple Team Exercise Framework

Black-box input-stage purification defense that neutralizes backdoor attacks on object detectors via corruption, diffusion reconstruction, and DBSCAN…

Evolutionary LLM jailbreak and guardrail framework that grows a reusable strategy pool via genetic mutation, Markov selection, and online adversarial…

Fine-tuning framework that applies first-order optimal safety calibration and periodic recalibration to LLMs, preserving safety-compatible updates…

Defense framework that mitigates malicious fine-tuning of LLMs using selective layer recovery and dynamic routing, with training, harmfulness…

Defense framework that keeps audio-language models frozen and adds a mid-layer risk gate with late-layer safety adapters to block audio jailbreaks at…