Related papers: ASTRA: Autonomous Spatial-Temporal Red-teaming for…
Autonomous AI agents powered by large language models are being deployed in production with capabilities including shell execution, file system access, database queries, and multi-party communication. Recent red teaming research…
The convergence of Information Technology and Operational Technology has exposed Industrial Control Systems to adaptive, intelligent adversaries that render static defenses obsolete. This paper introduces the Adversarial Resilience…
Red-teaming Vision-Language Models is essential for identifying vulnerabilities where adversarial image-text inputs trigger toxic outputs. Existing approaches treat image generation as a black box, returning only terminal toxicity scores…
The introduction of the European Union Artificial Intelligence Act, the NIST Artificial Intelligence Risk Management Framework, and related norms demands a better understanding and implementation of novel risk analysis approaches to…
Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new threat surface: unreliable search results can mislead agents into producing unsafe outputs.…
The trial and error approach of reinforcement learning (RL) results in high performance across many complex tasks, but it can also lead to unsafe behavior. Run time assurance (RTA) approaches can be used to assure safety of the agent during…
Time-series anomaly detection (TSAD) is a critical component in monitoring complex systems, yet modern deep learning-based detectors are often highly sensitive to localized input corruptions and structured noise. We propose ARTA…
Active Test-Time Adaptation (ATTA) improves model robustness under domain shift by selectively querying human annotations at deployment, but existing methods use heuristic uncertainty measures and suffer from low data selection efficiency,…
As artificial intelligence (AI) systems become increasingly embedded in critical societal functions, the need for robust red teaming methodologies continues to grow. In this forum piece, we examine emerging approaches to automating AI red…
Stellar activity interferes with precise radial velocity measurements and limits our ability to detect and characterize planets, particularly Earth-like planets. We introduce \aestra (Auto-Encoding STellar Radial-velocity and Activity), a…
Modern software engineers operate across 5-10 disconnected tools daily: GitHub, GitLab, Jira, Slack, calendar applications, CI dashboards, AI coding assistants, and container platforms. This fragmentation creates cognitive overhead that…
Data annotation is essential for supervised learning, yet producing accurate, unbiased, and scalable labels remains challenging as datasets grow in size and modality. Traditional human-centric pipelines are costly, slow, and prone to…
This paper presents ASTREA, the first agentic system executed on flight-heritage hardware (TRL 9) for autonomous spacecraft operations, with on-orbit operation aboard the International Space Station (ISS). Using thermal control as a…
The European Space Agency (ESA) uses an engine to perform tests in the Ground Segment infrastructure, specially the Operational Simulator. This engine uses many different tools to ensure the development of regression testing infrastructure…
Defending against today's increasingly sophisticated cyberattacks requires security analysts to continuously translate evolving attacker tradecraft into detection logic. This places defenders in a reactive posture, requiring constantly…
Generating tests that can reveal performance issues in large and complex software systems within a reasonable amount of time is a challenging task. On one hand, there are numerous combinations of input data values to explore. On the other…
Despite advances in language and speech technologies, no open-source system enables full speech-to-speech, multi-turn dialogue with integrated tool use and agentic reasoning. We introduce AURA (Agent for Understanding, Reasoning, and…
Artificial intelligence research increasingly depends on prolonged cycles of reproduction, debugging, and iterative refinement to achieve State-Of-The-Art (SOTA) performance, creating a growing need for systems that can accelerate the full…
The Copilot for Real-world Experimental Scientist (CRESt) system empowers researchers to control autonomous laboratories through conversational AI, providing a seamless interface for managing complex experimental workflows. We have enhanced…
As generative AI technologies find more and more real-world applications, the importance of testing their performance and safety seems paramount. "Red-teaming" has quickly become the primary approach to test AI models--prioritized by AI…