Related papers: BlackIce: A Containerized Red Teaming Toolkit for …
C-to-Rust transpilation is essential for modernizing legacy C code while enhancing safety and interoperability with modern Rust ecosystems. However, no dataset currently exists for evaluating whether a system can transpile C into safe Rust…
Computational materials science and chemistry span vast knowledge domains and fractured software ecosystems. Although large language models (LLMs) have demonstrated research capabilities, scaling monolithic agents to manage the rigor and…
The critical need for transparent and trustworthy machine learning in cybersecurity operations drives the development of this integrated Explainable AI (XAI) framework. Our methodology addresses three fundamental challenges in deploying AI…
Despite the integration of safety alignment and external filters, text-to-image (T2I) generative systems are still susceptible to producing harmful content, such as sexual or violent imagery. This raises serious concerns about unintended…
The integration of Large Language Models (LLMs) into Security Operations Centres (SOCs) presents a transformative, yet still evolving, opportunity to reduce analyst workload through human-AI collaboration. However, their real-world…
Autonomous web agents such as \textbf{OpenClaw} are rapidly moving into high-impact real-world workflows, but their security robustness under live network threats remains insufficiently evaluated. Existing benchmarks mainly focus on static…
This paper introduces v0.5 of the AI Safety Benchmark, which has been created by the MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to assess the safety risks of AI systems that use chat-tuned language models.…
Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…
The evolution of Large Language Models (LLMs) into autonomous agents has expanded the scope of AI coding from localized code generation to complex, repository-level, and execution-driven problem solving. However, current benchmarks…
Large Language Models (LLMs) have become instrumental in advancing software engineering (SE) tasks, showcasing their efficacy in code understanding and beyond. Like traditional SE tools, open-source collaboration is key in realising the…
The reuse of technologies and inherent complexity of most robotic systems is increasingly leading to robots with wide attack surfaces and a variety of potential vulnerabilities. Given their growing presence in public environments, security…
The application of Large Language Models (LLMs) for Automated Algorithm Discovery (AAD), particularly for optimisation heuristics, is an emerging field of research. This emergence necessitates robust, standardised benchmarking practices to…
As large language models (LLMs) grow in power and influence, ensuring their safety and preventing harmful output becomes critical. Automated red teaming serves as a tool to detect security vulnerabilities in LLMs without manual labor.…
Linux containers have risen in popularity in the last few years, making their way to commercial IT service offerings (such as PaaS), application deployments, and Continuous Delivery/Integration pipelines within various development teams.…
Cloud computing has changed online communities in three dimensions, which are scalability, adaptability and reduced overhead. But there are serious security concerns which are brought about by its distributed and multi-tenant…
The size of deep learning models in artificial intelligence (AI) software is increasing rapidly, hindering the large-scale deployment on resource-restricted devices (e.g., smartphones). To mitigate this issue, AI software compression plays…
Enterprise AI systems, built on large language models, retrieval pipelines and autonomous agents, introduce a class of risks that traditional software quality assurance was never designed to address. These systems are probabilistic,…
AI systems are entering critical domains like healthcare, finance, and defense, yet remain vulnerable to adversarial attacks. While AI red teaming is a primary defense, current approaches force operators into manual, library-specific…
With the rapid advancement and adoption of Audio Large Language Models (ALLMs), voice agents are now being deployed in high-stakes domains such as banking, customer service, and IT support. However, their vulnerabilities to adversarial…
Software vulnerabilities remain a critical security challenge, providing entry points for attackers into enterprise networks. Despite advances in security practices, the lack of high-quality datasets capturing diverse exploit behavior…