Search papers, labs, and topics across Lattice.
2
0
4
The effectiveness of antidistillation defenses hinges on the threat model used, revealing that current defenses may offer a false sense of security.
Production VLMs like GPT-4, Claude Opus, Gemini, and Grok can be easily manipulated into confidently providing false information via subtle adversarial perturbations to images, even without compromising model alignment.
