Search papers, labs, and topics across Lattice.
College of Computer Science and Technology/College of Software
5
0
6
4
ARIA can achieve a staggering 94.5% success rate in implanting covert backdoors in customized LLMs while ensuring high task performance.
Insecure coding preferences in LLM long-term memory can elevate vulnerability rates by over 50%, posing a critical security risk in code generation.
HealthClaw boosts answer accuracy for personal health management by over 45% while enhancing privacy protection in AI interactions.
LLMs can edit code 30% faster and cheaper without sacrificing accuracy, simply by learning to choose between generating full code and structure-aware diffs.
LLMs can bootstrap their code generation abilities without external supervision by leveraging semantic entropy to identify learnable tasks and behavioral consensus to filter noisy self-generated training signals.
