Search papers, labs, and topics across Lattice.
3
0
6
17
Invocation-time binding of call authority to workload state effectively eliminates post-authorization attacks, a critical vulnerability in remote LLM tool use.
JITterFlip reveals that targeting the JIT serving control plane can amplify attack effects by over 7 million times, exposing a major vulnerability in LLM inference systems.
Bridging the gap between ANNs and SNNs could revolutionize federated learning on resource-constrained devices, achieving high accuracy without sacrificing efficiency.
