Search papers, labs, and topics across Lattice.
Center of Excellence for Generative AI
4
0
6
4
A layered defense can thwart most self-state attacks on AI agents, but a hidden vulnerability persists that challenges current OS security paradigms.
$I$-$(OT)^2$ achieves over 10x faster Oblivious Transfer for IoT devices, making secure communication practical even on low-power hardware.
Stop leaking your business logic to users: this new framework lets you selectively verify SSI credentials without revealing *which* claims you're checking.
Turns out, you can spot LLM hallucinations just by looking at how tightly their answers cluster in embedding space, enabling a surprisingly effective way to flag bad responses with minimal labeling.
