Lorenzo Cavallaro

Veritas is a semantically grounded framework that detects memory corruption vulnerabilities in stripped binaries by combining static analysis, LLM-based reasoning, and runtime validation, achieving high recall and zero false positives on a curated benchmark.

The paper argues that the near-term impact of LLM-assisted vulnerability discovery is not simply an increase in zero-day volume, but a critical bottleneck in defender remediation throughput, shifting the focus to validation and patching capacity.

Antaeus is a framework that uses repository-level code context to detect logic vulnerabilities using LLM reasoning, reducing calls, cost, and triage effort.