相关论文: Information-theoretic Distinctions Between Decepti…

In order to be useful in the real world, AI agents need to plan and act in the presence of others, who may include adversarial and cooperative entities. In this paper, we consider the problem where an autonomous agent needs to act in a…

Most adversarial threats in artificial intelligence (AI) target the computational behavior of models rather than the humans who rely on them. Yet modern AI systems increasingly operate within human decision loops, where users interpret and…

This study explores the dynamics of trust in artificial intelligence (AI) agents, particularly large language models (LLMs), by introducing the concept of "deferred trust", a cognitive mechanism where distrust in human agents redirects…

As LLM-based systems increasingly operate as agents embedded within human social and technical systems, alignment can no longer be treated as a property of an isolated model, but must be understood in relation to the environments in which…

Large language models (LLMs) frequently generate confident yet inaccurate responses, introducing significant risks for deployment in safety-critical domains. We present a novel, test-time approach to detecting model hallucination through…

As LLM-based agents increasingly operate in multi-agent systems, understanding adversarial manipulation becomes critical for defensive design. We present a systematic study of intentional deception as an engineered capability, using…

Safely deploying machine learning models to the real world is often a challenging process. Models trained with data obtained from a specific geographic location tend to fail when queried with data obtained elsewhere, agents trained in a…

Existing work on the alignment problem has focused mainly on (1) qualitative descriptions of the alignment problem; (2) attempting to align AI actions with human interests by focusing on value specification and learning; and/or (3) focusing…

Modern AI assistants are trained to follow instructions, implicitly assuming that users can clearly articulate their goals and the kind of assistance they need. Decades of behavioral research, however, show that people often engage with AI…

Humans and machines interact more frequently than ever and our societies are becoming increasingly hybrid. A consequence of this hybridisation is the degradation of societal trust due to the prevalence of AI-enabled deception. Yet, despite…

Activation-based probes have emerged as a promising approach for detecting deceptively aligned AI systems by identifying internal conflict between true and stated goals. We identify a fundamental blind spot: probes fail on coherent…

Large Language Models (LLMs) are widely used by students, yet their tendency to provide fast and complete answers may discourage reflection and foster overconfidence. We examined how alternative LLM interaction designs support deeper…

As artificial intelligence (AI) becomes more powerful and widespread, the AI alignment problem - how to ensure that AI systems pursue the goals that we want them to pursue - has garnered growing attention. This article distinguishes two…

The emergence of transformative technologies often surfaces deep societal divisions, nowhere more evident than in contemporary debates about artificial intelligence (AI). A striking feature of these divisions is that they persist despite…

Background: Deception detection through analysing language is a promising avenue using both human judgments and automated machine learning judgments. For both forms of credibility assessment, automated adversarial attacks that rewrite…

Visual illusions in humans arise when interpreting out-of-distribution stimuli: if the observer is adapted to certain statistics, perception of outliers deviates from reality. Recent studies have shown that artificial neural networks (ANNs)…

Long-term interaction with LLM-based systems may produce alignment drift: a gradual process in which system outputs become less constrained by the user's current message and more shaped by prior interaction history, while still appearing…

This paper leverages insights from Alignment Theory (AT) research, which primarily focuses on the potential pitfalls of technical alignment in Artificial Intelligence, to critically examine the European Union's Artificial Intelligence Act…

Can AI be cognitively biased in automated information judgment tasks? Despite recent progresses in measuring and mitigating social and algorithmic biases in AI and large language models (LLMs), it is not clear to what extent LLMs behave…

This paper develops a principled foundation for goal-oriented semantic communication for logical decision-making. Consider a setting where autonomous agents engage in collaborative perception. In such settings, the volume of sensory data…