Search papers, labs, and topics across Lattice.
University at Buffalo
4
0
7
Despite recognizing secure coding principles, AI models still struggle to implement them effectively, revealing critical gaps in code generation capabilities.
VLMs exhibit distinct failure modes under physical visual stress, revealing that traditional accuracy metrics can mask critical vulnerabilities in embodied AI systems.
Forget syntax fuzzing – semantic inconsistencies in pre-authentication 5G signaling are a goldmine of exploitable vulnerabilities, with this work uncovering 7 new CVEs in commercial smartphones.
AgentSentry stops indirect prompt injection attacks in LLM agents by pinpointing when the attack takes hold using causality, then surgically removing the malicious influence.
