#adversarialml

A paper from Anthropic and collaborators shows that LLMs can be deliberately trained to act helpful...

AutoRobust uses RL to generate problem-space adversarial malware, real, functional binary/runtime...

Researchers demonstrated a class of AI-embedded targeted malware: the attack packs the targeting...

Researchers tested 50 emoji-augmented prompts across four open-source LLMs (Mistral 7B, Qwen 2 7B,...

Disesdi Susanna Cox and Niklas Bunzel's recent paper, "Quantifying the Risk of Transferred Black Box...