collaborators

9 papers

cs.CR2026

The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark

Jeremy Spence, Nicholas Assaderaghi, Jinhao Zhu +5

AI agents are rapidly improving in cybersecurity capabilities when the source code is available for analysis, yet much of the software most consequential to cybersecurity, includin…

cs.CR2026

Antiproof: Synthesizing Vulnerability Detectors and Proofs of Exploitability

Alon Shakevsky, Corban Villa, Ion Stoica +1

Antiproof is a system that automatically creates static vulnerability detectors using neuro‑symbolic synthesis and validates findings with executable proofs of exploitability, achi…

cs.CR2026

Prismata: Confining Cross-Site Prompt Injection in Web Agents

Corban Villa, Alp Eren Ozdarendeli, Sijun Tan +1

Autonomous web agents promise to automate everyday browsing tasks, but inherit one of the web's oldest attack surfaces. Cross-Site Scripting proved that mixing trusted and untruste…

cs.CR2026

ShannonProver: Towards Automating Formal Cryptographic Proofs

Yiping Ma, Yu-Lin Tsai, Mayank Rathee +4

Cryptographic proofs are produced at a scale that increasingly exceeds the community's ability to verify them manually. Machine-checked proofs offer a path toward scalable proof ve…

cs.CR2026

Chai: Agentic Discovery of Cryptographic Misuse Vulnerabilities

Corban Villa, Sohee Kim, Austin Chu +2

AI-assisted vulnerability discovery has proven effective for bug classes like memory safety, where instrumentation confirms memory violations and efficiently filters false positive…

cs.CR2026

Onyx: Cost-Efficient Disk-Oblivious ANN Search

Deevashwer Rathee, Jean-Luc Watson, Zirui Neil Zhao +2

Approximate nearest neighbor (ANN) search in AI systems increasingly handles sensitive data on third-party infrastructure. Trusted execution environments (TEEs) offer protection, b…