Related papers: Information-theoretic Distinctions Between Decepti…

As artificial intelligence (AI) systems become increasingly integral to organizational processes, they introduce new forms of fraud that are often subtle, systemic, and concealed within technical complexity. This paper introduces the…

Motivated by a study on deception and counter-deception, this paper addresses the problem of identifying an agent's target as it seeks to reach one of two targets in a given environment. In practice, an agent may initially follow a strategy…

Recent evidence suggests that frontier AI systems can exhibit agentic misalignment, generating and executing harmful actions derived from internally constructed goals, even without explicit user requests. Existing mitigation methods, such…

Generative AI (GenAI) poses a substantial threat to the integrity of information within the contemporary public sphere, which increasingly relies on social media platforms as intermediaries for news consumption. At present, most research…

Modeling plausible student misconceptions is critical for AI in education. In this work, we examine how large language models (LLMs) reason about misconceptions when generating multiple-choice distractors, a task that requires modeling…

As AI becomes more capable, we entrust it with more general and consequential tasks. The risks from failure grow more severe with increasing task scope. It is therefore important to understand how extremely capable AI models will fail: Will…

We study the tendency of AI systems to deceive by constructing a realistic simulation setting of a company AI assistant. The simulated company employees provide tasks for the assistant to complete, these tasks spanning writing assistance,…

Meetings often suffer from a lack of intentionality, such as unclear goals and straying off-topic. Identifying goals and maintaining their clarity throughout a meeting is challenging, as discussions and uncertainties evolve. Yet meeting…

In many contexts, lying -- the use of verbal falsehoods to deceive -- is harmful. While lying has traditionally been a human affair, AI systems that make sophisticated verbal statements are becoming increasingly prevalent. This raises the…

Deceptive behavior in AI systems is no longer theoretical: large language models strategically mislead without producing false statements, maintain deceptive strategies through safety training, and coordinate deception in multi-agent…

Model explanations such as saliency maps can improve user trust in AI by highlighting important features for a prediction. However, these become distorted and misleading when explaining predictions of images that are subject to systematic…

As the capabilities of large machine learning models continue to grow, and as the autonomy afforded to such models continues to expand, the spectre of a new adversary looms: the models themselves. The threat that a model might behave in a…

This paper presents a preliminary draft of a framework around the use of anthropomorphic deception, defined here as misleading users towards humanlike affordances in the design of autonomous systems. The goal is to promote reflection among…

Artificial Intelligence (AI) is rapidly being integrated into critical systems across various domains, from healthcare to autonomous vehicles. While its integration brings immense benefits, it also introduces significant risks, including…

Large language models are often described as sycophantic, in the sense that they appear to flatter users or mirror their beliefs. We argue that this label is conceptually misleading: sycophancy implies motives and strategic intent, which…

Finding claims that researchers have made considerable progress in artificial intelligence over the last several decades is easy. However, our everyday interactions with cognitive systems (e.g., Siri, Alexa, DALL-E) quickly move from…

As large language models (LLMs) become integrated into everyday and high-stakes decision-making, they inherit the ambiguity and biases of human language. While they produce fluent and coherent outputs, they rely on statistical pattern…

Model explanations such as saliency maps can improve user trust in AI by highlighting important features for a prediction. However, these become distorted and misleading when explaining predictions of images that are subject to systematic…

Large Language Models (LLMs) achieve strong performance through extended inference-time deliberation, yet how their reasoning failures arise remains poorly understood. By analyzing model-generated reasoning trajectories, we find that errors…

Linear probes are a promising approach for monitoring AI systems for deceptive behaviour. Previous work has shown that a linear classifier trained on a contrastive instruction pair and a simple dataset can achieve good performance. However,…