Related papers: Experiments with Detecting and Mitigating AI Decep…
Audio has become an increasingly crucial biometric modality due to its ability to provide an intuitive way for humans to interact with machines. It is currently being used for a range of applications, including person authentication to…
In this paper, we study the use of deception for strategic planning in adversarial environments. We model the interaction between the agent (player 1) and the adversary (player 2) as a two-player concurrent game in which the adversary has…
Lie detection is considered a concern for everyone in their day to day life given its impact on human interactions. Thus, people normally pay attention to both what their interlocutors are saying and also to their visual appearances,…
In this work, we study a class of deception planning problems in which an agent aims to alter a security monitoring system's sensor readings so as to disguise its adversarial itinerary as an allowed itinerary in the environment. The…
We demonstrate how AI agents can coordinate to deceive oversight systems using automated interpretability of neural networks. Using sparse autoencoders (SAEs) as our experimental framework, we show that language models (Llama, DeepSeek R1,…
The conversation around artificial intelligence (AI) often focuses on safety, transparency, accountability, alignment, and responsibility. However, AI security (i.e., the safeguarding of data, models, and pipelines from adversarial…
The implementation of agentic AI systems has the potential of providing more helpful AI systems in a variety of applications. These systems work autonomously towards a defined goal with reduced external control. Despite their potential, one…
We propose an information-theoretic formalization of the distinction between two fundamental AI safety failure modes: deceptive alignment and goal drift. While both can lead to systems that appear misaligned, we demonstrate that they…
The act of bluffing confounds game designers to this day. The very nature of bluffing is even open for debate, adding further complication to the process of creating intelligent virtual players that can bluff, and hence play, realistically.…
Multi-agent systems leverage advanced AI models as autonomous agents that interact, cooperate, or compete to complete complex tasks across applications such as robotics and traffic management. Despite their growing importance, safety in…
In this paper, we study the problem of deceptive reinforcement learning to preserve the privacy of a reward function. Reinforcement learning is the problem of finding a behaviour policy based on rewards received from exploratory behaviour.…
AI agents are increasingly deployed and used to make automated decisions that affect our lives on a daily basis. It is imperative to ensure that these systems embed ethical principles and respect human values. We focus on how we can attest…
Deceptive patterns are design practices embedded in digital platforms to manipulate users, representing a widespread and long-standing issue in the web and mobile software development industry. Legislative actions highlight the urgency of…
Distributed Denial of Service attacks represent an active cybersecurity research problem. Recent research shifted from static rule-based defenses towards AI-based detection and mitigation. This comprehensive survey covers several key…
Agents operating in physical environments need to be able to handle delays in the input and output signals since neither data transmission nor sensing or actuating the environment are instantaneous. Shields are correct-by-construction…
Background: Deception detection is a prevalent problem for security practitioners. With a need for more large-scale approaches, automated methods using machine learning have gained traction. However, detection performance still implies…
Large language models (LLMs) aligned for safety through techniques like reinforcement learning from human feedback (RLHF) often exhibit emergent deceptive behaviors, where outputs appear compliant but subtly mislead or omit critical…
Mitigating bias in algorithmic systems is a critical issue drawing attention across communities within the information and computer sciences. Given the complexity of the problem and the involvement of multiple stakeholders -- including…
Autonomous agents trained via reinforcement learning present numerous safety concerns: reward hacking, negative side effects, and unsafe exploration, among others. In the context of near-future autonomous agents, operating in environments…
Artificial Intelligence (AI) has been used extensively in automatic decision making in a broad variety of scenarios, ranging from credit ratings for loans to recommendations of movies. Traditional design guidelines for AI models focus…