Search papers, labs, and topics across Lattice.
3
0
4
Natural backdoor vulnerabilities are not just a theoretical concern; they are prevalent in CodeLMs and can significantly compromise code security.
Code dataset watermarking can be stealthy, robust, and effective across both source-code and decompilation tasks by injecting repressible poisoned features that only activate upon watermark removal.
LLMs can now translate C to Rust with near-perfect syntactic correctness and significantly improved semantic correctness by incorporating program structure information into the translation process.