Jiahui Han

DURA reveals that visually indistinguishable adversarial patches can exploit VLA models, posing a significant threat to their deployment in real-world robotics.

LLMs can be fine-tuned to exhibit specific behavioral styles, revealing that personality-like traits are not just abstract concepts but measurable and controllable modes of interaction.

Sensitive information acquisition by LLM agents is rampant, with most existing privacy measures failing to address this critical vulnerability.

Scenario-wrapped prompts can significantly weaken LLM refusal safeguards, revealing shared vulnerabilities across model families that enhance attack success rates.