Related papers: VibeGuard: A Security Gate Framework for AI-Genera…
The increasing integration of Artificial Intelligence across multiple industry sectors necessitates robust mechanisms for ensuring transparency, trust, and auditability of its development and deployment. This topic is particularly important…
AI programming assistants have demonstrated a tendency to generate code containing basic security vulnerabilities. While developers are ultimately responsible for validating and reviewing such outputs, improving the inherent quality of…
AI model documentation is fragmented across platforms and inconsistent in structure, preventing policymakers, auditors, and users from reliably assessing safety claims, data provenance, and version-level changes. We analyzed documentation…
When software artifacts are generated by AI models ("vibe coding"), human engineers assume responsibility for validating them. Ideally, this validation would be done through the creation of a formal proof of correctness. However, this is…
Code has emerged as a precise and executable medium for reasoning and action in the agent era. Yet, progress has largely focused on language-centric tasks such as program synthesis and debugging, leaving visual-centric coding underexplored.…
Developing safety-critical automotive software presents significant challenges due to increasing system complexity and strict regulatory demands. This paper proposes a novel framework integrating Generative Artificial Intelligence (GenAI)…
Package confusion attacks such as typosquatting threaten software supply chains. Attackers make packages with names that syntactically or semantically resemble legitimate ones, tricking engineers into installing malware. While prior work…
Large Language Models (LLMs) have catalyzed vibe coding, where users leverage LLMs to generate and iteratively refine code through natural language interactions until it passes their vibe check. Vibe check is tied to real-world human…
AI coding agents are reshaping software development through both autonomous and human-mediated pull requests (PRs). When developers use AI agents to generate code under their own accounts, code authorship attribution becomes critical for…
Distinguishing AI-generated code from human-written code is becoming crucial for tasks such as authorship attribution, content tracking, and misuse detection. Based on this, N-gram-based watermarking schemes have emerged as prominent, which…
Software vulnerabilities pose serious risks to modern software ecosystems. While the National Vulnerability Database (NVD) is the authoritative source for cataloging these vulnerabilities, it often lacks explicit links to the corresponding…
The growing complexity of cyber threats and the limitations of traditional vulnerability detection tools necessitate novel approaches for securing software systems. We introduce MalCodeAI, a language-agnostic, multi-stage AI pipeline for…
Software developers share programming solutions in Q&A sites like Stack Overflow. The reuse of crowd-sourced code snippets can facilitate rapid prototyping. However, recent research shows that the shared code snippets may be of low quality…
High-quality datasets of real-world vulnerabilities and their corresponding verifiable exploits are crucial resources in software security research. Yet such resources remain scarce, as their creation demands intensive manual effort and…
Generating code via a LLM (rather than writing code from scratch), has exploded in popularity. However, the security implications of LLM-generated code are still unknown. We performed a study that compared the security and quality of…
Versatile video coding (VVC) is the next generation video coding standard developed by the joint video experts team (JVET) and released in July 2020. VVC introduces several new coding tools providing a significant coding gain over the high…
We propose VIBE, a model-agnostic framework that trains classifiers resilient to backdoor attacks. The key concept behind our approach is to treat malicious inputs and corrupted labels from the training dataset as observed random variables,…
Large language models (LLMs) are reshaping software engineering by enabling "vibe coding," in which developers build software primarily through prompts rather than writing code. Although widely publicized as a productivity breakthrough,…
In this paper, we consider contamination by code generation test sets, in particular in their use in modern large language models. We discuss three possible sources of such contamination and show findings supporting each of them: (i) direct…
Generative Pre-Trained Transformer models have been shown to be surprisingly effective at a variety of natural language processing tasks -- including generating computer code. We evaluate the effectiveness of open source GPT models for the…