Related papers: MalCodeAI: Autonomous Vulnerability Detection and …

In cybersecurity, security analysts constantly face the challenge of mitigating newly discovered vulnerabilities in real-time, with over 300,000 vulnerabilities identified since 1999. The sheer volume of known vulnerabilities complicates…

LLM coding agents now generate code at an unprecedented scale, yet LLM-generated code introduces cybersecurity vulnerabilities into codebases without human involvement. Even when frontier models are explicitly asked to write secure…

Open-source ecosystems such as NPM and PyPI are increasingly targeted by supply chain attacks, yet existing detection methods either depend on fragile handcrafted rules or data-driven features that fail to capture evolving attack semantics.…

This study presents a quantitative evaluation of the code quality and security of five prominent Large Language Models (LLMs): Claude Sonnet 4, Claude 3.7 Sonnet, GPT-4o, Llama 3.2 90B, and OpenCoder 8B. While prior research has assessed…

The evaluation of large language model refusal on malicious-coding tasks now spans at least thirteen publicly released prompt corpora (AdvBench, the CyberSecEval family, RMCBench, RedCode, MCGMark, JailbreakBench, CySecBench, MalwareBench,…

Detecting vulnerabilities is vital for software security, yet deep learning-based vulnerability detectors (DLVD) face a data shortage, which limits their effectiveness. Data augmentation can potentially alleviate the data shortage, but…

Software vulnerabilities can result in catastrophic cyberattacks that increasingly threaten business operations. Consequently, ensuring the safety of software systems has become a paramount concern for both private and public sectors.…

State-of-the-art large language models (LLMs) have demonstrated impressive code generation capabilities but struggle with real-world software engineering tasks, such as revising source code to address code reviews, hindering their practical…

Robust robotic manipulation requires reliable failure detection and recovery. Although recent Vision-Language Models (VLMs) show promise in robot failure detection, their generalization is severely limited by the scarcity and narrow…

Large Language Models (LLMs) have recently demonstrated strong capabilities in code-related tasks, but their robustness in code reasoning under perturbations remains underexplored. We introduce CodeCrash, a stress-testing framework with…

Large Language Models (LLMs) demonstrate strong capabilities in general coding tasks but encounter two key challenges when optimizing code: (i) the complexity of writing optimized code (such as performant CUDA kernels and competition-level…

Cryptographic algorithms are fundamental to modern security, yet their implementations frequently harbor subtle logic flaws that are hard to detect. We introduce CryptoScope, a novel framework for automated cryptographic vulnerability…

Detecting security vulnerabilities in software before they are exploited has been a challenging problem for decades. Traditional code analysis methods have been proposed, but are often ineffective and inefficient. In this work, we model…

LLMs are increasingly explored for malware analysis; however, current LLM-based malware attribution remains limited by unsupported indicators and insufficient code-level grounding for identifying malicious and vulnerable code segments. To…

Code review is an essential process to ensure the quality of software that identifies potential software issues at an early stage of software development. Among all software issues, security issues are the most important to identify, as…

Large Language Models (LLMs) have demonstrated significant potential in automated software security, particularly in vulnerability detection. However, existing benchmarks primarily focus on isolated, single-vulnerability samples or…

Recent advancements in Large Language Model (LLM) safety have primarily focused on mitigating attacks crafted in natural language or common ciphers (e.g. Base64), which are likely integrated into newer models' safety training. However, we…

Software vulnerabilities, caused by unintentional flaws in source code, are a primary root cause of cyberattacks. Static analysis of source code has been widely used to detect these unintentional defects introduced by software developers.…

The adoption of Large Language Models (LLMs) for automated software vulnerability patching has shown promising outcomes on carefully curated evaluation sets. Nevertheless, existing datasets predominantly rely on superficial validation…

Large Language Models are a promising tool for automated vulnerability detection, thanks to their success in code generation and repair. However, despite widespread adoption, a critical question remains: Are LLMs truly effective at…