Related papers: Learning Password Best Practices Through In-Task I…

Safe control methods are often intended to behave safely even in worst-case human uncertainties. However, humans may exploit such safety-first systems, which results in greater risk for everyone. Despite their significance, no prior work…

Efficient password cracking is a critical aspect of digital forensics, enabling investigators to decrypt protected content during criminal investigations. Traditional password cracking methods, including brute-force, dictionary and…

A common assumption in machine learning is that training data are i.i.d. samples from some distribution. Processes that generate i.i.d. samples are, in a sense, uninformative---they produce data without regard to how good this data is for…

Language models are transforming the ways that their users engage with the world. Despite impressive capabilities, over-consumption of language model outputs risks propagating unchecked errors in the short-term and damaging human…

As the frontier of machine learning applications moves further into human interaction, multiple concerns arise regarding automated decision-making. Two of the most critical issues are fairness and data privacy. On the one hand, one must…

As language models are increasingly deployed as autonomous agents in high-stakes settings, ensuring that they reliably follow user-defined rules has become a critical safety concern. To this end, we study whether language models exhibit…

Imitation Learning has provided a promising approach to learning complex robot behaviors from expert demonstrations. However, learned policies can make errors that lead to safety violations, which limits their deployment in safety-critical…

Humans demonstrate a variety of interesting behavioral characteristics when performing tasks, such as selecting between seemingly equivalent optimal actions, performing recovery actions when deviating from the optimal trajectory, or…

AI-supported tools can help learners overcome challenges in programming education by providing adaptive assistance. However, existing research often focuses on individual tools rather than deriving broader design recommendations. A key…

Recent work has demonstrated that problems-- particularly imitation learning and structured prediction-- where a learner's predictions influence the input-distribution it is tested on can be naturally addressed by an interactive approach…

Failures are challenging for learning to control physical systems since they risk damage, time-consuming resets, and often provide little gradient information. Adding safety constraints to exploration typically requires a lot of prior…

The last half-decade has seen a steep rise in the number of contributions on safe learning methods for real-world robotic deployments from both the control and reinforcement learning communities. This article provides a concise but holistic…

We define a practical method to quantify the trade-off between security and operational friction in modern identity-centric programs. We introduce the Security Friction Quotient (SFQ), a bounded composite index that combines a residual-risk…

Social robots are increasingly recognized as valuable supporters in the field of well-being coaching. They can function as independent coaches or provide support alongside human coaches, and healthcare professionals. In coaching…

Random exploration is one of the main mechanisms through which reinforcement learning (RL) finds well-performing policies. However, it can lead to undesirable or catastrophic outcomes when learning online in safety-critical environments. In…

In safety-critical robot planning or control, manually specifying safety constraints or learning them from demonstrations can be challenging. In this article, we propose a certifiable alignment method for a robot to learn a safety…

This paper puts forward the concept that learning to take safe actions in unknown environments, even with probability one guarantees, can be achieved without the need for an unbounded number of exploratory trials. This is indeed possible,…

In settings like vaccination registries, individuals act after observing others, and the resulting public records can expose private information. We study privacy-preserving sequential learning, where agents add endogenous noise to their…

Preference learning is a widely adopted post-training technique that aligns large language models (LLMs) to human preferences and improves specific downstream task capabilities. In this work we systematically investigate how specific…

The promise of interaction between intelligent conversational agents and humans is that models can learn from such feedback in order to improve. Unfortunately, such exchanges in the wild will not always involve human utterances that are…