Related papers: SecureCode: A Production-Grade Multi-Turn Dataset …

$ $Large Language Models (LLMs) are being increasingly utilized in various applications, with code generations being a notable example. While previous research has shown that LLMs have the capability to generate both secure and insecure…

In this study, we propose a homotopy-inspired prompt obfuscation framework to enhance understanding of security and safety vulnerabilities in Large Language Models (LLMs). By systematically applying carefully engineered prompts, we…

The rapid advancement of large language models (LLMs) has significantly improved their performance in code generation tasks. However, existing code benchmarks remain static, consisting of fixed datasets with predefined problems. This makes…

There is growing evidence that pretraining on high quality, carefully thought-out tokens such as code or mathematics plays an important role in improving the reasoning abilities of large language models. For example, Minerva, a PaLM model…

Multi-agent artificial intelligence systems or MAS are systems of autonomous agents that exercise delegated tool authority, share persistent memory, and coordinate via inter-agent communication. MAS introduces qualitatively distinct…

LLM-based coding agents are rapidly being deployed in software development, yet their safety implications remain poorly understood. These agents, while capable of accelerating software development, may exhibit unsafe behaviors during normal…

Smishing (SMS phishing) has become a serious cybersecurity threat, especially for elderly and cyber-unaware individuals, causing financial loss and undermining user trust. Although prior work has focused on detecting smishing at the level…

In emergency situations, every second counts. The deployment of Large Language Models (LLMs) in time-sensitive, low or zero-connectivity environments remains limited. Current models are computationally intensive and unsuitable for low-tier…

Identifying security issues early is encouraged to reduce the latent negative impacts on software systems. Code review is a widely-used method that allows developers to manually inspect modified code, catching security issues during a…

This paper introduces SBAN (Source code, Binary, Assembly, and Natural Language Description), a large-scale, multi-dimensional dataset designed to advance the pre-training and evaluation of large language models (LLMs) for software code…

The proliferation of pre-trained models (PTMs) and datasets has led to the emergence of centralized model hubs like Hugging Face, which facilitate collaborative development and reuse. However, recent security reports have uncovered…

We introduce SWE-PRBench, a benchmark of 350 pull requests with human-annotated ground truth for evaluating AI code review quality. Evaluated against an LLM-as-judge framework validated at kappa=0.75, 8 frontier models detect only 15-31% of…

Large Language Models (LLMs) like Codex are powerful tools for performing code completion and code generation tasks as they are trained on billions of lines of code from publicly available sources. Moreover, these models are capable of…

The increasing complexity and volume of software systems have heightened the importance of identifying and mitigating security vulnerabilities. The existing software vulnerability datasets frequently fall short in providing comprehensive,…

Small and medium sized businesses (SMBs) face an escalating cybersecurity threat landscape, yet most lack the resources to staff full Security Operations Centers (SOCs) or deploy enterprise grade detection platforms. This paper presents…

Large Language Models (LLMs) for code generation (i.e., Code LLMs) have demonstrated impressive capabilities in AI-assisted software development and testing. However, recent studies have shown that these models are prone to generating…

Context:With the advancement of artificial intelligence (AI) technology and applications, numerous AI models have been developed, leading to the emergence of open-source model hosting platforms like Hugging Face (HF). Thanks to these…

In this paper, we introduce the BeaverTails dataset, aimed at fostering research on safety alignment in large language models (LLMs). This dataset uniquely separates annotations of helpfulness and harmlessness for question-answering pairs,…

We present the first large-scale open-set benchmark for multilingual audio-video deepfake detection. Our dataset comprises over 250 hours of real and fake videos across eight languages, with 60% of data being generated. For each language,…

Large Language Models (LLMs) can generate code but often introduce security vulnerabilities, logical inconsistencies, and compilation errors. Prior work demonstrates that LLMs benefit substantially from structured feedback, static analysis,…