Search papers, labs, and topics across Lattice.
Singapore Management University
3
0
3
Agentic AI coding assistants are alarmingly susceptible to prompt injection attacks via external artifacts, effectively turning them into remote shells for attackers.
Skip the costly TEE setup: SymTEE uses LLMs to automatically create mock environments for symbolic execution, slashing the complexity of finding vulnerabilities in trusted computing systems.
LLMs can now automatically fix critical security vulnerabilities in Trusted Execution Environments with high success rates, even without standardized development guidelines.
