Related papers: Is Vibe Coding Safe? Benchmarking Vulnerability of…
In the context of the rising interest in code language models (code LMs) and vulnerability detection, we study the effectiveness of code LMs for detecting vulnerabilities. Our analysis reveals significant shortcomings in existing…
The majority of software developers use or are planning to use Artificial Intelligence (AI) tools in their development processes. Their top reasons include improving productivity and faster learning. In fact, Large Language Model…
We witness an increasing usage of AI-assistants even for routine (classroom) programming tasks. However, the code generated on basis of a so called "prompt" by the programmer does not always meet accepted security standards. On the one…
Software vulnerabilities (SVs) have emerged as a prevalent and critical concern for safety-critical security systems. This has spurred significant advancements in utilizing AI-based methods, including machine learning and deep learning, for…
Developing high-performance software is a complex task that requires specialized expertise. We introduce GSO, a benchmark for evaluating language models' capabilities in developing high-performance software. We develop an automated pipeline…
Open Source Software (OSS) security and resilience are worldwide phenomena hampering economic and technological innovation. OSS vulnerabilities can cause unauthorized access, data breaches, network disruptions, and privacy violations,…
The application layer of Bluetooth Low Energy (BLE) is a growing source of security vulnerabilities, as developers often neglect to implement critical protections such as encryption, authentication, and freshness. While formal verification…
Software testing is a critical activity to ensure that software complies with its specification. However, current software testing activities tend not to be completely effective when applied in specific software domains in Virtual Reality…
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…
Generative AI agents are reshaping human-computer interaction, shifting users from direct task execution to supervising machine-driven actions, especially the rise of "vibe coding" in programming. Yet little is known about how screen reader…
Coding agents powered by large language models are increasingly expected to perform realistic software maintenance tasks beyond isolated issue resolution. Existing benchmarks have shifted toward realistic software evolution, but they rarely…
Virtual Reality (VR) is an emerging technique that provides a unique real-time experience for users. VR technologies have provided revolutionary user experiences in various scenarios (e.g., training, education, product/architecture design,…
Software security mainly studies vulnerability detection: is my code vulnerable today? This hinders risk estimation, so new approaches are emerging to forecast the occurrence of future vulnerabilities. While useful, these approaches are…
Prior works on training software engineering agents have explored utilizing existing resources such as issues on GitHub repositories to construct software engineering tasks and corresponding test suites. These approaches face two key…
Code vulnerability detection (CVD) is essential for addressing and preventing system security issues, playing a crucial role in ensuring software security. Previous learning-based vulnerability detection methods rely on either fine-tuning…
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.…
Large Language Models are expanding beyond being a tool humans use and into independent agents that can observe an environment, reason about solutions to problems, make changes that impact those environments, and understand how their…
Large language models (LLMs) have recently enabled coding agents capable of generating, executing, and revising visualization code. However, existing models often fail in practical workflows due to limited language coverage, unreliable…
Large language models (LLMs) have brought significant advancements to code generation, benefiting both novice and experienced developers. However, their training using unsanitized data from open-source repositories, like GitHub, introduces…
Academic laboratories face mounting resource constraints: budgets are tightening, grant overheads are potentially being capped, and the market rate for data-science talent significantly outstrips university compensation. Vibe coding, which…