Related papers: ASTRA: Autonomous Spatial-Temporal Red-teaming for…
Adversarial testing of large language models (LLMs) is crucial for their safe and responsible deployment. We introduce a novel approach for automated generation of adversarial evaluation datasets to test the safety of LLM generations on new…
[Context] AI assistants, like GitHub Copilot and Cursor, are transforming software engineering. While several studies highlight productivity improvements, their impact on maintainability requires further investigation. [Objective] This…
As software development practices increasingly adopt AI-powered tools, ensuring that such tools can support secure coding has become critical. This study evaluates the effectiveness of GitHub Copilot's recently introduced code review…
[Background/Context] AI assistants like GitHub Copilot are transforming software engineering; several studies have highlighted productivity improvements. However, their impact on code quality, particularly in terms of maintainability,…
We present the Virtual Research Assistant (VRA) of the ATLAS sky survey which performs preliminary eyeballing on our clean transient data stream. The VRA uses Histogram Based Gradient Boosted Decision Tree Classifiers trained on real data…
Following the recent release of AI assistants, such as OpenAI's ChatGPT and GitHub Copilot, the software industry quickly utilized these tools for software development tasks, e.g., generating code or consulting AI for advice. While recent…
Training AI agents to proactively assist humans in daily activities, from routine household tasks to urgent safety situations, requires large-scale visual data. However, capturing such scenarios in the real world is often difficult, costly,…
All of the frontier AI companies have published safety frameworks where they define capability thresholds and risk mitigations that determine how they will safely develop and deploy their models. Adoption of systematic approaches to risk…
Validating the safety of autonomous systems generally requires the use of high-fidelity simulators that adequately capture the variability of real-world scenarios. However, it is generally not feasible to exhaustively search the space of…
A runtime assurance system (RTA) for a given plant enables the exercise of an untrusted or experimental controller while assuring safety with a backup (or safety) controller. The relevant computational design problem is to create a logic…
A persistent challenge in accessible computing is ensuring developers produce web UI code that supports assistive technologies. Despite numerous specialized accessibility tools, novice developers often remain unaware of them, leading to…
AI-based code assistants are promising tools that can facilitate and speed up code development. They exploit machine learning algorithms and natural language processing to interact with developers, suggesting code snippets (e.g., method…
Modern web test suites rot. A UI refactor breaks locators, a timing change causes race conditions, and within weeks developers abandon the suite entirely. This paper presents an AI-driven autonomous testing framework that addresses these…
Zero Trust Architectures (ZTA) fundamentally redefine network security by adopting a "trust nothing, verify everything" approach that requires identity verification for all access. Conventional discrete access control measures have proven…
The real-world deployment of Vision-Language-Action (VLA) models remains limited by the risk of unpredictable and irreversible physical harm. However, we currently lack effective mechanisms to proactively detect these physical safety risks…
Text-to-image models like stable diffusion and DALLE-3 still struggle with multi-turn image editing. We decompose such a task as an agentic workflow (path) of tool use that addresses a sequence of subtasks by AI tools of varying costs.…
State-of-the-art deep neural networks require large-scale labeled training data that is often expensive to obtain or not available for many tasks. Weak supervision in the form of domain-specific rules has been shown to be useful in such…
AI systems have the potential to produce both benefits and harms, but without rigorous and ongoing adversarial evaluation, AI actors will struggle to assess the breadth and magnitude of the AI risk surface. Researchers from the field of…
The emergence of autonomous, high-velocity Agentic AI systems is creating an internal assurance scalability crisis. Point-in-time, document-based audits cannot keep pace with non deterministic behaviour and distributed deployments of agents…
Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…