Antiproof: Synthesizing Vulnerability Detectors and Proofs of Exploitability

arXiv:2607.12316 · cs.CR · Submitted 2026-07-14 · Read on arXiv

Alon Shakevsky, Corban Villa, Ion Stoica, Raluca Ada Popa

cs.CR

Submitted: 2026-07-14

Comments: 17 pages, 7 figures

Code: https://github.com/google/oss-fuzz

Project page: https://google.github.io/security-research/kernelctf/rules.html

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 24× in this paper · explained in 2 episodes
• Verifier — 8× in this paper · explained in 2 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Known Exploited Vulnerabilities — 5× in this paper
• AI Agents — 4× in this paper · explained in 2 episodes
• Arbiter — 3× in this paper · explained in 1 episode
• Hallucination — 3× in this paper · explained in 3 episodes
• Iterative Refinement — 3× in this paper · explained in 3 episodes
• Verification — 3× in this paper · explained in 2 episodes
• Allocator — 2× in this paper · explained in 1 episode
• Cybersecurity and Infrastructure Security Agency — 2× in this paper
• Program Dependence Graph — 2× in this paper
• RAG — 2× in this paper · explained in 3 episodes
• Reward Hacking — 2× in this paper · explained in 8 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Actor — 1× in this paper · explained in 3 episodes
• Analyzer — 1× in this paper · explained in 1 episode
• Capture The Flag — 1× in this paper
• Consistency — 1× in this paper · explained in 3 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• QLCoder: A Query Synthesizer For Static Analysis of Security Vulnerabilities
• Neuro-symbolic Static Analysis with LLM-generated Vulnerability Patterns
• RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing
• Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents
• Guiding Symbolic Execution with Static Analysis and LLMs for Vulnerability Discovery
• AnyPoC: Universal Proof-of-Concept Test Generation for Scalable LLM-Based Bug Detection
• FaultLine: Automated Proof-of-Vulnerability Generation Using LLM Agents
• From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEs
• A Survey of Context Engineering for Large Language Models
• LLM-based Vulnerability Detection at Project Scale: An Empirical Study
• Why Language Models Hallucinate
• CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale
• Reducing False Positives in Static Bug Detection with LLMs: An Empirical Study in Industry
• Argus: Reorchestrating Static Analysis via a Multi-Agent Ensemble for Full-Chain Security Vulnerability Detection
• Multi-Agent Taint Specification Extraction for Vulnerability Detection
• Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask
• Vulnerability Detection with Code Language Models: How Far Are We?
• CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities
• Incalmo: An Autonomous LLM-assisted System for Red Teaming Multi-Host Networks
• VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs