Related papers: The Obfuscation Atlas: Mapping Where Honesty Emerg…

Deep learning-based object detection has become ubiquitous in the last decade due to its high accuracy in many real-world applications. With this growing trend, these models are interested in being attacked by adversaries, with most of the…

Offline reinforcement learning can enable policy learning from pre-collected, sub-optimal datasets without online interactions. This makes it ideal for real-world robots and safety-critical scenarios, where collecting online data or expert…

In the era of the internet and smart devices, the detection of malware has become crucial for system security. Malware authors increasingly employ obfuscation techniques to evade advanced security solutions, making it challenging to detect…

Agents trained in simulation may make errors in the real world due to mismatches between training and execution environments. These mistakes can be dangerous and difficult to discover because the agent cannot predict them a priori. We…

Deep reinforcement learning has proven remarkably useful in training agents from unstructured data. However, the opacity of the produced agents makes it difficult to ensure that they adhere to various requirements posed by human engineers.…

The honesty of large language models (LLMs) is a critical alignment challenge, especially as advanced systems with chain-of-thought (CoT) reasoning may strategically deceive humans. Unlike traditional honesty issues on LLMs, which could be…

Previous work has shown that training "helpful-only" LLMs with reinforcement learning on a curriculum of gameable environments can lead models to generalize to egregious specification gaming, such as editing their own reward function or…

Deception plays a key role in adversarial or strategic interactions for the purpose of self-defence and survival. This paper introduces a general framework and solution to address deception. Most existing approaches for deception consider…

Machine-learning based intrusion detection classifiers are able to detect unknown attacks, but at the same time, they may be susceptible to evasion by obfuscation techniques. An adversary intruder which possesses a crucial knowledge about a…

An increasingly common socio-technical problem is people being taken in by offers that sound ``too good to be true'', where persuasion and trust shape decision-making. This paper investigates how \abr{ai} can help detect these deceptive…

Current AI regulations require discarding sensitive features (e.g., gender, race, religion) in the algorithm's decision-making process to prevent unfair outcomes. However, even without sensitive features in the training set, algorithms can…

Recent years have seen an explosion of interest in autonomous cyber defence agents trained to defend computer networks using deep reinforcement learning. These agents are typically trained in cyber gym environments using dense, highly…

Recent advances in Large Language Models (LLMs) have incorporated planning and reasoning capabilities, enabling models to outline steps before execution and provide transparent reasoning paths. This enhancement has reduced errors in…

It has been shown that adversaries can craft example inputs to neural networks which are similar to legitimate inputs but have been created to purposely cause the neural network to misclassify the input. These adversarial examples are…

In offline reinforcement learning (RL) agents are trained using a logged dataset. It appears to be the most natural route to attack real-life applications because in domains such as healthcare and robotics interactions with the environment…

While reinforcement learning (RL) algorithms have been successfully applied to numerous tasks, their reliance on neural networks makes their behavior difficult to understand and trust. Counterfactual explanations are human-friendly…

Large language models sometimes produce false or misleading responses. Two approaches to this problem are honesty elicitation -- modifying prompts or weights so that the model answers truthfully -- and lie detection -- classifying whether a…

The safety of decentralized reinforcement learning (RL) is a challenging problem since malicious agents can share their poisoned policies with benign agents. The paper investigates a cooperative backdoor attack in a decentralized…

Obfuscation of computer programs has historically been approached either as a practical but \textit{ad hoc} craft to make reverse engineering subjectively difficult, or as a sound theoretical investigation unfortunately detached from the…

As Large Language Models (LLMs) transition into autonomous agentic roles, the risk of deception-defined behaviorally as the systematic provision of false information to satisfy external incentives-poses a significant challenge to AI safety.…