
EpiReal-Bench
Red-teaming benchmark and black-box attack framework for evaluating visual misinformation risks in commercial image generators, with 10k false-claim…
adversarial-attackai-securityeducation+4

Red-teaming benchmark and black-box attack framework for evaluating visual misinformation risks in commercial image generators, with 10k false-claim…

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

Research code for measuring jailbreak attack success rates (ASR and stepwise ASR) against LLMs, with implementations of attacks such as GCG and…