Search papers, labs, and topics across Lattice.
4
0
8
5
JUDGESTEALER reveals that efficient extraction of LLM judging capabilities is possible without extensive querying, achieving remarkable accuracy across multiple evaluation protocols.
Uncovering critical security and privacy vulnerabilities in foundation-model-powered robots could redefine how we approach their deployment in real-world applications.
MIXGUARD achieves robust privacy protection in split learning without sacrificing model utility, outperforming existing defenses against advanced data reconstruction attacks.
LLM agents are shockingly vulnerable to stealthy economic DoS attacks that inflate costs by up to 658x, even while returning correct answers.
