Search papers, labs, and topics across Lattice.
State Key Laboratory of Novel Software Technology
8
0
6
15
Insecure coding preferences in LLM long-term memory can elevate vulnerability rates by over 50%, posing a critical security risk in code generation.
LLM-based evaluators can outperform traditional metrics in method name prediction, but the real breakthrough comes from a novel approach that enhances name quality through summarization and refinement.
LLMs can now effectively analyze deep learning frameworks for bugs without the need for costly runtime execution, revealing 31 previously undetected issues in PyTorch.
Natural backdoor vulnerabilities are not just a theoretical concern; they are prevalent in CodeLMs and can significantly compromise code security.
Prompt injection remains the leading attack vector against LLM agents, but emerging threats like persistent state corruption demand urgent attention.
LLMs can be taught to avoid repeating past mistakes in vulnerability repair, boosting performance by up to 39% over state-of-the-art methods.
Existing REST API testing tools miss critical business logic, but LoBREST finds 38 bugs that no other tool can.
Most "agent skills" hyped for boosting LLMs in software engineering provide almost no benefit in real-world tasks, with 80% yielding zero pass-rate improvement.
