Search papers, labs, and topics across Lattice.
Affiliation:
3
0
5
Cloned outputs from LLMs can be detected with over 87% accuracy using behavioral signatures, revealing significant vulnerabilities in prompt security.
Targeted bit-flip attacks can cripple Vision-Language-Action models, reducing their success rates to zero with just a few flips in key layers.
Corrupting the imagination in VLA policies is 60 times more effective than random perturbations, exposing a critical vulnerability in safety mechanisms.
