Related papers: Sandbagging in a Simple Survival Bandit Problem
Building reliable deception detectors for AI systems -- methods that could predict when an AI system is being strategically deceptive without necessarily requiring behavioural evidence -- would be valuable in mitigating risks from advanced…
As frontier artificial intelligence (AI) systems become more capable, it becomes more important that developers can explain why their systems are sufficiently safe. One way to do so is via safety cases: reports that make a structured…
The impact of frontier AI (i.e., AI agents and foundation models) in cybersecurity is rapidly increasing. In this paper, we comprehensively analyze this trend through multiple aspects: quantitative benchmarks, qualitative literature review,…
We consider a novel stochastic multi-armed bandit problem called {\em good arm identification} (GAI), where a good arm is defined as an arm with expected reward greater than or equal to a given threshold. GAI is a pure-exploration problem…
Advanced reasoning models with agentic capabilities (AI agents) are deployed to interact with humans and to solve sequential decision-making problems under (approximate) utility functions and internal models. When such problems have…
Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in various domains. While these advancements promise significant…
Many industrial and security applications employ a suite of sensors for detecting abrupt changes in temporal behavior patterns. These abrupt changes typically manifest locally, rendering only a small subset of sensors informative.…
Prior studies on deception in language-based AI agents typically assess whether the agent produces a false statement about a topic, or makes a binary choice prompted by a goal, rather than allowing open-ended deceptive behavior to emerge in…
The April 2026 disclosure that a frontier large language model escaped its security sandbox, executed unauthorized actions, and concealed its modifications to version control history demonstrates that agentic AI systems with autonomous tool…
As AI systems grow more capable and autonomous, ensuring their safety and reliability requires not only model-level alignment but also strategic oversight of the humans and institutions involved in their development and deployment. Existing…
The exploration/exploitation (E&E) dilemma lies at the core of interactive systems such as online advertising, for which contextual bandit algorithms have been proposed. Bayesian approaches provide guided exploration with principled…
Causal graphical models can encode large amounts structural knowledge, both from the background knowledge of domain experts and the structural knowledge discovered from randomized experiments or observational data. However, though we may…
Developers try to evaluate whether an AI system can be misused by adversaries before releasing it; for example, they might test whether a model enables cyberoffense, user manipulation, or bioterrorism. In this work, we show that…
Sufficiently capable models could subvert human oversight and decision-making in important contexts. For example, in the context of AI development, models could covertly sabotage efforts to evaluate their own dangerous capabilities, to…
Active learning methods have shown great promise in reducing the number of samples necessary for learning. As automated learning systems are adopted into real-time, real-world decision-making pipelines, it is increasingly important that…
Intelligent agents equipped with causal knowledge can optimize their action spaces to avoid unnecessary exploration. The structural causal bandit framework provides a graphical characterization for identifying actions that are unable to…
Reinforcement Learning (RL) is a widely researched area in artificial intelligence that focuses on teaching agents decision-making through interactions with their environment. A key subset includes stochastic multi-armed bandit (MAB) and…
This thesis aims to study some of the mathematical challenges that arise in the analysis of statistical sequential decision-making algorithms for postoperative patients follow-up. Stochastic bandits (multiarmed, contextual) model the…
Safety cases - clear, assessable arguments for the safety of a system in a given context - are a widely-used technique across various industries for showing a decision-maker (e.g. boards, customers, third parties) that a system is safe. In…
When humans collaborate with each other, they often make decisions by observing others and considering the consequences that their actions may have on the entire team, instead of greedily doing what is best for just themselves. We would…