Antaeus: Hunting Repository-Level Logic Vulnerabilities via Context-Grounded LLM Reasoning

Abstract

LLM-based vulnerability detectors have shown promising results in identifying memory-safety bugs and vulnerability classes whose violations can often be expressed through established security properties. Logic vulnerabilities, however, pose a different challenge, as their identification requires inferring application-specific security invariants and implicit assumptions about intended behavior. Even frontier agentic models struggle because these invariants are often implicit and buried among unr

Categories

@misc{armillotta2026antaeus,
  title = {{Antaeus: Hunting Repository-Level Logic Vulnerabilities via Context-Grounded LLM Reasoning}},
  author = {Michele Armillotta and Nicolò Romandini and Rebecca Montanari and Lorenzo Cavallaro},
  year = {2026},
  month = jul,
  eprint = {2607.01138},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2607.01138}
}