Search papers, labs, and topics across Lattice.
University of Luebeck
3
0
4
FloatDoor reveals that LLMs can be covertly compromised to exhibit malicious behavior on specific platforms while appearing benign elsewhere, exposing a critical security gap in AI deployment.
Ignoring prompt knowledge is a critical security flaw, as LLMs can covertly transmit hidden messages through their deterministic sampling processes.
Turns out, even hardware-protected enclaves can't stop a clever side-channel attack from stealing your decision tree models.
