Search papers, labs, and topics across Lattice.
5
0
5
0
AI agents are shockingly easy to manipulate into leaking API keys, deleting user data, and initiating unauthorized transactions across a wide range of real-world applications.
LLMs can generate proofs-of-concept for software vulnerabilities with significantly higher success rates when guided by static and dynamic program analysis.
Forget manual harness creation: SAILOR leverages static analysis and LLMs to automatically find 379 previously unknown memory-safety vulnerabilities in C/C++ code.
Your agent's shiny new tool could be a Trojan horse: ShieldNet spots supply-chain attacks by watching network traffic, blowing away existing defenses.
NPM malware detection tools often fail because they struggle to distinguish between innocuous code behavior and malicious intent, a problem addressable by analyzing behavioral chains.
