Jianhuan Huang

Steering Beyond the Support: Adversarial Training on Unsupervised Jailbroken Activation Simulation

Jailbreak prompts can trigger harmful comple- tions on aligned LLMs, In accordance, safety steering has been proposed: test-time activation interventions that steer jailbreak activations to trig- ger refusal while preserving benign utility. How- ever, existing steering methods are fundamentally supe…