Research Papers

Many existing AI music generation tools rely on text prompts, complex interfaces, or instrument-like controls, which may require musical or technical knowledge that non-musicians do not possess. This paper introduces DeformTune, a prototype system that combines a tactile deformable interface with the MeasureVAE model to explore more intuitive, embodied, and explainable AI interaction. We conducted a preliminary study with 11 adult participants without formal musical training to investigate their experience with AI-assisted music creation. Thematic analysis of their feedback revealed recurring challenge--including unclear control mappings, limited expressive range, and the need for guidance throughout use. We discuss several design opportunities for enhancing explainability of AI, including multimodal feedback and progressive interaction support. These findings contribute early insights toward making AI music systems more explainable and empowering for novice users.

Climate extremes present escalating risks to agriculture intensifying the need for reliable multi-hazard early warning systems (EWS). The situation is evolving due to climate change and hence such systems should have the intelligent to continue to learn from recent climate behaviours. However, traditional single-hazard forecasting methods fall short in capturing complex interactions among concurrent climatic events. To address this deficiency, in this paper, we combine sequential deep learning models and advanced Explainable Artificial Intelligence (XAI) techniques to introduce a multi-hazard forecasting framework for agriculture. In our experiments, we utilize meteorological data from four prominent agricultural regions in the United States (between 2010 and 2023) to validate the predictive accuracy of our framework on multiple severe event types, which are extreme cold, floods, frost, hail, heatwaves, and heavy rainfall, with tailored models for each area. The framework uniquely integrates attention mechanisms with TimeSHAP (a recurrent XAI explainer for time series) to provide comprehensive temporal explanations revealing not only which climatic features are influential but precisely when their impacts occur. Our results demonstrate strong predictive accuracy, particularly with the BiLSTM architecture, and highlight the system's capacity to inform nuanced, proactive risk management strategies. This research significantly advances the explainability and applicability of multi-hazard EWS, fostering interdisciplinary trust and effective decision-making process for climate risk management in the agricultural industry.

AGI Racing is the view that it is in the self-interest of major actors in AI development, especially powerful nations, to accelerate their frontier AI development to build highly capable AI, especially artificial general intelligence (AGI), before competitors have a chance. We argue against AGI Racing. First, the downsides of racing to AGI are much higher than portrayed by this view. Racing to AGI would substantially increase catastrophic risks from AI, including nuclear instability, and undermine the prospects of technical AI safety research to be effective. Second, the expected benefits of racing may be lower than proponents of AGI Racing hold. In particular, it is questionable whether winning the race enables complete domination over losers. Third, international cooperation and coordination, and perhaps carefully crafted deterrence measures, constitute viable alternatives to racing to AGI which have much smaller risks and promise to deliver most of the benefits that racing to AGI is supposed to provide. Hence, racing to AGI is not in anyone's self-interest as other actions, particularly incentivizing and seeking international cooperation around AI issues, are preferable.

Microelectronic systems are widely used in many sensitive applications (e.g., manufacturing, energy, defense). These systems increasingly handle sensitive data (e.g., encryption key) and are vulnerable to diverse threats, such as, power side-channel attacks, which infer sensitive data through dynamic power profile. In this paper, we present a novel framework, POLARIS for mitigating power side channel leakage using an Explainable Artificial Intelligence (XAI) guided masking approach. POLARIS uses an unsupervised process to automatically build a tailored training dataset and utilize it to train a masking model.The POLARIS framework outperforms state-of-the-art mitigation solutions (e.g., VALIANT) in terms of leakage reduction, execution time, and overhead across large designs.

AI has become integral to safety-critical areas like autonomous driving systems (ADS) and robotics. The architecture of recent autonomous systems are trending toward end-to-end (E2E) monolithic architectures such as large language models (LLMs) and vision language models (VLMs). In this paper, we review different architectural solutions and then evaluate the efficacy of common safety analyses such as failure modes and effect analysis (FMEA) and fault tree analysis (FTA). We show how these techniques can be improved for the intricate nature of the foundational models, particularly in how they form and utilize latent representations. We introduce HySAFE-AI, Hybrid Safety Architectural Analysis Framework for AI Systems, a hybrid framework that adapts traditional methods to evaluate the safety of AI systems. Lastly, we offer hints of future work and suggestions to guide the evolution of future AI safety standards.

Modern network intrusion detection systems (NIDS) frequently utilize the predictive power of complex deep learning models. However, the "black-box" nature of such deep learning methods adds a layer of opaqueness that hinders the proper understanding of detection decisions, trust in the decisions and prevent timely countermeasures against such attacks. Explainable AI (XAI) methods provide a solution to this problem by providing insights into the causes of the predictions. The majority of the existing XAI methods provide explanations which are not convenient to convert into actionable countermeasures. In this work, we propose a novel diffusion-based counterfactual explanation framework that can provide actionable explanations for network intrusion attacks. We evaluated our proposed algorithm against several other publicly available counterfactual explanation algorithms on 3 modern network intrusion datasets. To the best of our knowledge, this work also presents the first comparative analysis of existing counterfactual explanation algorithms within the context of network intrusion detection systems. Our proposed method provide minimal, diverse counterfactual explanations out of the tested counterfactual explanation algorithms in a more efficient manner by reducing the time to generate explanations. We also demonstrate how counterfactual explanations can provide actionable explanations by summarizing them to create a set of global rules. These rules are actionable not only at instance level but also at the global level for intrusion attacks. These global counterfactual rules show the ability to effectively filter out incoming attack queries which is crucial for efficient intrusion detection and defense mechanisms.

Artificial intelligence enables unprecedented attacks on human cognition, yet cybersecurity remains predominantly device-centric. This paper introduces the "Think First, Verify Always" (TFVA) protocol, which repositions humans as 'Firewall Zero', the first line of defense against AI-enabled threats. The protocol is grounded in five operational principles: Awareness, Integrity, Judgment, Ethical Responsibility, and Transparency (AIJET). A randomized controlled trial (n=151) demonstrated that a minimal 3-minute intervention produced statistically significant improvements in cognitive security task performance, with participants showing an absolute +7.87% gains compared to controls. These results suggest that brief, principles-based training can rapidly enhance human resilience against AI-driven cognitive manipulation. We recommend that GenAI platforms embed "Think First, Verify Always" as a standard prompt, replacing passive warnings with actionable protocols to enhance trustworthy and ethical AI use. By bridging the gap between technical cybersecurity and human factors, the TFVA protocol establishes human-empowered security as a vital component of trustworthy AI systems.

Recent advancements in machine learning have emphasized the need for transparency in model predictions, particularly as interpretability diminishes when using increasingly complex architectures. In this paper, we propose leveraging prediction uncertainty as a complementary approach to classical explainability methods. Specifically, we distinguish between aleatoric (data-related) and epistemic (model-related) uncertainty to guide the selection of appropriate explanations. Epistemic uncertainty serves as a rejection criterion for unreliable explanations and, in itself, provides insight into insufficient training (a new form of explanation). Aleatoric uncertainty informs the choice between feature-importance explanations and counterfactual explanations. This leverages a framework of explainability methods driven by uncertainty quantification and disentanglement. Our experiments demonstrate the impact of this uncertainty-aware approach on the robustness and attainability of explanations in both traditional machine learning and deep learning scenarios.

Humans learn to prefer trustworthy AI over human partners

Yaomin Jiang, Levin Brinkmann, Anne-Marie Nussberger +3

Partner selection is crucial for cooperation and hinges on communication. As artificial agents, especially those powered by large language models (LLMs), become more autonomous, intelligent, and persuasive, they compete with humans for partnerships. Yet little is known about how humans select between human and AI partners and adapt under AI-induced competition pressure. We constructed a communication-based partner selection game and examined the dynamics in hybrid mini-societies of humans and bots powered by a state-of-the-art LLM. Through three experiments (N = 975), we found that bots, though more prosocial than humans and linguistically distinguishable, were not selected preferentially when their identity was hidden. Instead, humans misattributed bots' behaviour to humans and vice versa. Disclosing bots' identity induced a dual effect: it reduced bots' initial chances of being selected but allowed them to gradually outcompete humans by facilitating human learning about the behaviour of each partner type. These findings show how AI can reshape social interaction in mixed societies and inform the design of more effective and cooperative hybrid systems.

Transcription Factor Binding Site (TFBS) prediction is crucial for understanding gene regulation and various biological processes. This study introduces a novel Mixture of Experts (MoE) approach for TFBS prediction, integrating multiple pre-trained Convolutional Neural Network (CNN) models, each specializing in different TFBS patterns. We evaluate the performance of our MoE model against individual expert models on both in-distribution and out-of-distribution (OOD) datasets, using six randomly selected transcription factors (TFs) for OOD testing. Our results demonstrate that the MoE model achieves competitive or superior performance across diverse TF binding sites, particularly excelling in OOD scenarios. The Analysis of Variance (ANOVA) statistical test confirms the significance of these performance differences. Additionally, we introduce ShiftSmooth, a novel attribution mapping technique that provides more robust model interpretability by considering small shifts in input sequences. Through comprehensive explainability analysis, we show that ShiftSmooth offers superior attribution for motif discovery and localization compared to traditional Vanilla Gradient methods. Our work presents an efficient, generalizable, and interpretable solution for TFBS prediction, potentially enabling new discoveries in genome biology and advancing our understanding of transcriptional regulation.

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 information. This paper introduces adversarial activation patching, a novel mechanistic interpretability framework that leverages activation patching as an adversarial tool to induce, detect, and mitigate such deception in transformer-based models. By sourcing activations from "deceptive" prompts and patching them into safe forward passes at specific layers, we simulate vulnerabilities and quantify deception rates. Through toy neural network simulations across multiple scenarios (e.g., 1000 trials per setup), we demonstrate that adversarial patching increases deceptive outputs to 23.9% from a 0% baseline, with layer-specific variations supporting our hypotheses. We propose six hypotheses, including transferability across models, exacerbation in multimodal settings, and scaling effects. An expanded literature review synthesizes over 20 key works in interpretability, deception, and adversarial attacks. Mitigation strategies, such as activation anomaly detection and robust fine-tuning, are detailed, alongside ethical considerations and future research directions. This work advances AI safety by highlighting patching's dual-use potential and provides a roadmap for empirical studies on large-scale models.

Effective AI governance requires structured approaches for stakeholders to access and verify AI system behavior. With the rise of large language models, Natural Language Explanations (NLEs) are now key to articulating model behavior, which necessitates a focused examination of their characteristics and governance implications. We draw on Explainable AI (XAI) literature to create an updated XAI taxonomy, adapted to prompt-based NLEs, across three dimensions: (1) Context, including task, data, audience, and goals; (2) Generation and Presentation, covering generation methods, inputs, interactivity, outputs, and forms; and (3) Evaluation, focusing on content, presentation, and user-centered properties, as well as the setting of the evaluation. This taxonomy provides a framework for researchers, auditors, and policymakers to characterize, design, and enhance NLEs for transparent AI systems.