The European Union Artificial Intelligence Act mandates clear stakeholder responsibilities in developing and deploying machine learning applications to avoid substantial fines, prioritizing private and secure data processing with data remaining at its origin. Federated Learning (FL) enables the training of generative AI Models across data siloes, sharing only model parameters while improving data security. Since FL is a cooperative learning paradigm, clients and servers naturally share legal responsibility in the FL pipeline. Our work contributes to clarifying the roles of both parties, explains strategies for shifting responsibilities to the server operator, and points out open technical challenges that we must solve to improve FL's practical applicability under the EU AI Act.

This paper introduces the GazeRace method for drone navigation, employing a computer vision interface facilitated by eye-tracking technology. This interface is designed to be compatible with a single camera and uses a convolutional neural network to convert eye movements into control commands for the drone. Experimental validation demonstrates that users equipped with the eye-tracking interface achieve comparable performance to a traditional remote control interface when completing a drone racing task. Ten participants completed flight tests in which they navigated a drone through a racing track in a Gazebo simulation environment. Users reduced drone trajectory length by 18% (73.44 m vs. 89.29 m) using the eye-tracking interface to navigate racing gates effectively. The time taken to complete the route using the eye-tracking method (average of 70.01 seconds) was only 3.5% slower than using the remote control method (also average of 70.01 seconds), indicating the good efficiency of the interface. It is also worth mentioning that four of the participants completed the race with an average time that was 25.9% faster than the other participants. In addition, users evaluated highly the performance (M = 34.0, SD = 14.2) and low frustration (M = 30.5, SD = 9.2) with the eye-tracking interface compared to performance (M = 63.0, SD = 10.1) and frustration (M = 49.0, SD = 11.7) with the baseline remote controller. The hedonic quality (M = 1.65, SD = 0.45) was also evaluated high by the users in the UEQ questionnaire.

The field of Neural-Symbolic (NeSy) systems is growing rapidly. Proposed approaches show great promise in achieving symbiotic unions of neural and symbolic methods. However, each NeSy system differs in fundamental ways. There is a pressing need for a unifying theory to illuminate the commonalities and differences in approaches and enable further progress. In this paper, we introduce Neural-Symbolic Energy-Based Models (NeSy-EBMs), a unifying mathematical framework for discriminative and generative modeling with probabilistic and non-probabilistic NeSy approaches. We utilize NeSy-EBMs to develop a taxonomy of modeling paradigms focusing on a system's neural-symbolic interface and reasoning capabilities. Additionally, we introduce a suite of learning techniques for NeSy-EBMs. Importantly, NeSy-EBMs allow the derivation of general expressions for gradients of prominent learning losses, and we provide four learning approaches that leverage methods from multiple domains, including bilevel and stochastic policy optimization. Finally, we present Neural Probabilistic Soft Logic (NeuPSL), an open-source NeSy-EBM library designed for scalability and expressivity, facilitating real-world application of NeSy systems. Through extensive empirical analysis across multiple datasets, we demonstrate the practical advantages of NeSy-EBMs in various tasks, including image classification, graph node labeling, autonomous vehicle situation awareness, and question answering.

With increasingly sophisticated large language models (LLMs), the potential for abuse rises drastically. As a submission to the Swiss AI Safety Prize, we present a novel type of metamorphic malware leveraging LLMs for two key processes. First, LLMs are used for automatic code rewriting to evade signature-based detection by antimalware programs. The malware then spreads its copies via email by utilizing an LLM to socially engineer email replies to encourage recipients to execute the attached malware. Our submission includes a functional minimal prototype, highlighting the risks that LLMs pose for cybersecurity and underscoring the need for further research into intelligent malware.

The widespread adoption of large language models (LLMs) has raised concerns about their safety and reliability, particularly regarding their vulnerability to adversarial attacks. In this paper, we propose a novel perspective that attributes this vulnerability to reward misspecification during the alignment process. We introduce a metric ReGap to quantify the extent of reward misspecification and demonstrate its effectiveness and robustness in detecting harmful backdoor prompts. Building upon these insights, we present ReMiss, a system for automated red teaming that generates adversarial prompts against various target aligned LLMs. ReMiss achieves state-of-the-art attack success rates on the AdvBench benchmark while preserving the human readability of the generated prompts. Detailed analysis highlights the unique advantages brought by the proposed reward misspecification objective compared to previous methods.

As AI systems appear to exhibit ever-increasing capability and generality, assessing their true potential and safety becomes paramount. This paper contends that the prevalent evaluation methods for these systems are fundamentally inadequate, heightening the risks and potential hazards associated with AI. I argue that a reformation is required in the way we evaluate AI systems and that we should look towards cognitive sciences for inspiration in our approaches, which have a longstanding tradition of assessing general intelligence across diverse species. We will identify some of the difficulties that need to be overcome when applying cognitively-inspired approaches to general-purpose AI systems and also analyse the emerging area of "Evals". The paper concludes by identifying promising research pathways that could refine AI evaluation, advancing it towards a rigorous scientific domain that contributes to the development of safe AI systems.

Multi-agent AI systems can be used for simulating collective decision-making in scientific and practical applications. They can also be used to introduce a diverse group discussion step in chatbot pipelines, enhancing the cultural sensitivity of the chatbot's responses. These applications, however, are predicated on the ability of AI agents to reliably adopt assigned personas and mimic human interactions. To evaluate the ability of LLM agents to satisfy these requirements, we examine AI agent ensembles engaged in cultural collaboration and debate by analyzing their private responses and chat transcripts. Our findings suggest that multi-agent discussions can encourage collective decisions that reflect diverse perspectives, yet this benefit is tempered by the agents' susceptibility to conformity due to perceived peer pressure and challenges in maintaining consistent personas and opinions. Instructions that encourage debate in support of one's opinions rather than collaboration increase the rate of inconstancy. Without addressing the factors we identify, the full potential of multi-agent frameworks for producing more culturally diverse AI outputs or more realistic simulations of group decision-making will remain untapped.

Recent literature has proposed approaches that learn control policies with high performance while maintaining safety guarantees. Synthesizing Hamilton-Jacobi (HJ) reachable sets has become an effective tool for verifying safety and supervising the training of reinforcement learning-based control policies for complex, high-dimensional systems. Previously, HJ reachability was limited to verifying low-dimensional dynamical systems -- this is because the computational complexity of the dynamic programming approach it relied on grows exponentially with the number of system states. To address this limitation, in recent years, there have been methods that compute the reachability value function simultaneously with learning control policies to scale HJ reachability analysis while still maintaining a reliable estimate of the true reachable set. These HJ reachability approximations are used to improve the safety, and even reward performance, of learned control policies and can solve challenging tasks such as those with dynamic obstacles and/or with lidar-based or vision-based observations. In this survey paper, we review the recent developments in the field of HJ reachability estimation in reinforcement learning that would provide a foundational basis for further research into reliability in high-dimensional systems.

This paper investigates neuron dropout as a post-processing bias mitigation for deep neural networks (DNNs). Neural-driven software solutions are increasingly applied in socially critical domains with significant fairness implications. While neural networks are exceptionally good at finding statistical patterns from data, they may encode and amplify existing biases from the historical data. Existing bias mitigation algorithms often require modifying the input dataset or the learning algorithms. We posit that the prevalent dropout methods that prevent over-fitting during training by randomly dropping neurons may be an effective and less intrusive approach to improve the fairness of pre-trained DNNs. However, finding the ideal set of neurons to drop is a combinatorial problem. We propose NeuFair, a family of post-processing randomized algorithms that mitigate unfairness in pre-trained DNNs via dropouts during inference after training. Our randomized search is guided by an objective to minimize discrimination while maintaining the model's utility. We show that our design of randomized algorithms is effective and efficient in improving fairness (up to 69%) with minimal or no model performance degradation. We provide intuitive explanations of these phenomena and carefully examine the influence of various hyperparameters of search algorithms on the results. Finally, we empirically and conceptually compare NeuFair to different state-of-the-art bias mitigators.

Words often carry different meanings for people from diverse backgrounds. Today's era of social polarization demands that we choose words carefully to prevent miscommunication, especially in political communication and journalism. To address this issue, we introduce the Bridging Dictionary, an interactive tool designed to illuminate how words are perceived by people with different political views. The Bridging Dictionary includes a static, printable document featuring 796 terms with summaries generated by a large language model. These summaries highlight how the terms are used distinctively by Republicans and Democrats. Additionally, the Bridging Dictionary offers an interactive interface that lets users explore selected words, visualizing their frequency, sentiment, summaries, and examples across political divides. We present a use case for journalists and emphasize the importance of human agency and trust in further enhancing this tool. The deployed version of Bridging Dictionary is available at https://dictionary.ccc-mit.org/.