Search papers, labs, and topics across Lattice.
Affiliation:
3
0
4
Malicious developers can exploit the interaction between benign-looking wrappers and crafted metadata to manipulate AI outputs without altering model weights, revealing a significant security vulnerability in AI deployments.
A stealthy backdoor attack can exploit circuit cutting in VQAs, amplifying energy output while evading detection.
SQD's robustness is challenged by hardware choices, revealing that initial layout and noise strategies can drastically impact performance before stabilizing.
