arXiv AI

SWE-Test: Benchmarking LLM Vulnerability Discovery via Input Prediction

arXiv Machine Learning
Aug 27

FuzzingBrain-Bench V1: Evaluating Open-Ended Bug Discovery by LLMs

FuzzingBrain‑Bench V1 is a new benchmark that tests large language models (LLMs) on their ability to discover software bugs in open‑source projects. Unlike prior benchmarks that focus on a single target vulnerability, this benchmark gives models a Docker‑based harness and asks them to generate inputs that trigger as many distinct crashes as possible. The first version contains 77 challenges from 43 projects (36 C, 32 C++, 9 Java/JVM) and evaluates Claude Haiku 4.5, Claude Sonnet 4.6, and Claude Opus 4.8, with Claude Opus 4.8 achieving the highest score by triggering crashes in 60 of 77 challenges.

By Ze Sheng, Aleksandar Kezic, Zhicheng Chen, Jeff Huang
arXiv AI
Jun 30

Reinforcement Learning for Software Vulnerability Analysis: A Systematic Review with Emphasis on C/C++ Source Code and Static Analysis

arXiv:2606. 28403v1 Announce Type: cross Abstract: Vulnerability detection in C/C++ software remains a major security challenge due to code complexity, manual memory management, and the limitations of traditional static analysis.

By Bruno Caro-V\'asquez, Carola Figueroa-Flores, Gast\'on Marquez
arXiv AI
Jun 9

SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios

arXiv:2509. 22097v5 Announce Type: replace-cross Abstract: Large language model-powered code agents are rapidly transforming software engineering, yet the security risks of their generated code have become a critical concern.

By Junkai Chen, Huihui Huang, Yunbo Lyu, Junwen An, Jieke Shi, Chengran Yang, Ting Zhang, Haoye Tian, Yikun Li, Zhenhao Li, Xin Zhou, Xing Hu, David Lo
arXiv AI
Sep 4

PatchBench: Evaluating AI Agents for Vulnerability Patching

PatchBench introduces a benchmark to evaluate AI agents on realistic vulnerability patching tasks, addressing two key threats to validity: patch memorization and surface-level fixes that merely suppress crashes. The study finds that 25% of agent patches resemble historical developer patches, and that PoC-only validation inflates success rates by 1.83× on average. PatchBench mitigates these issues by selecting vulnerabilities whose true fixes lie outside the crash stack, migrating historical vulnerabilities into new contexts, and employing rigorous validation for security and semantic correctness.

By Chihao Shen, Jiacheng Li, Aastha Mahajan, Jeffery Siyuan Tian, Yonghwi Kwon, Yizheng Chen
arXiv AI
6d ago

When LLM Decompilers Recompile More and Preserve Less

The paper examines how large‑language‑model (LLM) decompilers, which produce clean, idiomatic C code, are currently evaluated mainly on recompilability and passing shipped tests. It shows that these metrics can mask significant behavioral differences: a decompiled function may recompile and pass all tests yet diverge on other inputs or lose disclosed vulnerabilities. To address this, the authors propose Decompile‑Diverge, a behavioral oracle that synthesizes drivers, fuzzes inputs, and compares the decompiled code’s behavior to the original, revealing divergences in up to 13% of cases and exposing gaps in current evaluation suites.

By Chang Liu, Edward Raff, Kristopher Micinski