Related papers: Fundamental Limits of Black-Box Safety Evaluation:…

The scaling of Large Language Models (LLMs) has exposed a critical gap between their performance on static benchmarks and their fragility in dynamic, information-rich environments. While models excel at isolated tasks, the computational…

Edge AI is often framed as model compression and deployment under tight constraints. We argue a stronger operational thesis: Edge AI in realistic deployments is necessarily adaptive. In long-horizon operation, a fixed (non-adaptive)…

Extended interaction with large language models (LLMs) has been linked to the reinforcement of delusional beliefs, a phenomenon attracting growing clinical and public concern. Yet most empirical work evaluates model safety in brief…

Following the rapid increase in Artificial Intelligence (AI) capabilities in recent years, the AI community has voiced concerns regarding possible safety risks. To support decision-making on the safe use and development of AI systems, there…

Although large language models (LLMs) have transformed AI, they still make mistakes and can explore unproductive reasoning paths. Self-correction capability is essential for deploying LLMs in safety-critical applications. We uncover a…

Black-box Artificial Intelligence (AI) methods, e.g. deep neural networks, have been widely utilized to build predictive models that can extract complex relationships in a dataset and make predictions for new unseen data records. However,…

Machine-learned black-box policies are ubiquitous for nonlinear control problems. Meanwhile, crude model information is often available for these problems from, e.g., linear approximations of nonlinear dynamics. We study the problem of…

Black box systems for automated decision making, often based on machine learning over (big) data, map a user's features into a class or a score without exposing the reasons why. This is problematic not only for lack of transparency, but…

Black-box tuning is an emerging paradigm for adapting large language models (LLMs) to better achieve desired behaviors, particularly when direct access to model parameters is unavailable. Current strategies, however, often present a dilemma…

This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history…

Enterprise agents increasingly operate inside scoped retrieval systems, delegated workflows, and policy-constrained evidence environments. In these settings, access control can be enforced correctly while the system still produces an answer…

An increasing number of machine learning models have been deployed in domains with high stakes such as finance and healthcare. Despite their superior performances, many models are black boxes in nature which are hard to explain. There are…

The rapid emergence of Large Language Models (LLMs) has precipitated a profound paradigm shift in Artificial Intelligence, delivering monumental engineering successes that increasingly impact modern society. However, a critical paradox…

As the development of Large Models (LMs) progresses rapidly, their safety is also a priority. In current Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) safety workflow, evaluation, diagnosis, and alignment are…

Affordances and permissions are promising and timely safety levers for mitigating Loss of Control (LoC) threats in high-stakes deployment contexts, such as national security. Deployers in defense and intelligence could rely on several…

Identifying controlled safety invariant sets (CSISs) is essential for safety-critical systems. This paper addresses the problem of computing CSISs for black-box discrete-time systems, where the dynamics are unknown and only limited…

Recent published evidence from frontier laboratories shows that contemporary AI models can recognise evaluation contexts, latently represent them, and behave differently under those contexts than under deployment-continuous conditions.…

As deep neural networks are deployed in safety-critical domains such as autonomous driving and medical diagnosis, stakeholders need explanations that are interpretable but also trustworthy with formal guarantees. Existing XAI methods fall…

As machine learning black boxes are increasingly being deployed in real-world applications, there has been a growing interest in developing post hoc explanations that summarize the behaviors of these black boxes. However, existing…

Nowadays, the use of machine learning models is becoming a utility in many applications. Companies deliver pre-trained models encapsulated as application programming interfaces (APIs) that developers combine with third party components and…