Research Papers

Open-source status should not shield generative artificial intelligence systems from ethical or legal accountability. Through a rigorous analysis of regulatory, legal, and policy frameworks, this Article contends that open-source GenAI must be held to the same standards as proprietary systems. While recognizing the value of openness for scientific advancement, I propose a narrowly tailored safe harbor for bona fide, non-commercial research, conditioned on strict compliance with defined criteria. This Article critically examines and refutes the core claims of open-source exceptionalism--namely, that open-source GenAI disrupts entrenched oligopolies, democratizes access, and uniquely drives innovation. The evidence shows that open-source GenAI can facilitate unlawful conduct, exacerbate environmental harms, and reinforce existing power structures. Rhetoric around "democratization" and "innovation" often serves as an unsubstantiated basis for regulatory exemptions not afforded to proprietary systems. This Article ultimately advocates for a framework that promotes responsible AI development, balancing openness with robust legal and ethical safeguards and a clear-eyed assessment of societal impacts.

Backchannels are subtle listener responses, such as nods, smiles, or short verbal cues like "yes" or "uh-huh," which convey understanding and agreement in conversations. These signals provide feedback to speakers, improve the smoothness of interaction, and play a crucial role in developing human-like, responsive AI systems. However, the expression of backchannel behaviors is often significantly influenced by individual differences, operating across multiple scales: from instant dynamics such as response intensity (frame-level) to temporal patterns such as frequency and rhythm preferences (sequence-level). This presents a complex pattern recognition problem that contemporary emotion recognition methods have yet to fully address. Particularly, existing individualized methods in emotion recognition often operate at a single scale, overlooking the complementary nature of multi-scale behavioral cues. To address these challenges, we propose a novel Cascaded Multi-Scale Individual Standardization Network (CMIS-Net) that extracts individual-normalized backchannel features by removing person-specific neutral baselines from observed expressions. Operating at both frame and sequence levels, this normalization allows model to focus on relative changes from each person's baseline rather than absolute expression values. Furthermore, we introduce an implicit data augmentation module to address the observed training data distributional bias, improving model generalization. Comprehensive experiments and visualizations demonstrate that CMIS-Net effectively handles individual differences and data imbalance, achieving state-of-the-art performance in backchannel agreement detection.

Large Language Models are susceptible to jailbreak attacks that bypass built-in safety guardrails (e.g., by tricking the model with adversarial prompts). We propose Concept Alignment and Concept Manipulation CALM, an inference-time method that suppresses harmful concepts by modifying latent representations of the last layer of the model, without retraining. Leveraging concept whitening technique from Computer Vision combined with orthogonal projection, CALM removes unwanted latent directions associated with harmful content while preserving model performance. Experiments show that CALM reduces harmful outputs and outperforms baseline methods in most metrics, offering a lightweight approach to AI safety with no additional training data or model fine-tuning, while incurring only a small computational overhead at inference.

Attribution Graphs and Causal Probing for Mechanistic Discovery and Bias Repair in Multimodal Generative Learning

Noor Islam S. Mohammad, Uluğ Bayazıt

We treat the internals of generative models as mechanistic objects rather than black boxes. We introduce \textbf{Attribution Graphs} (AGs), which extend GradCAM++ to circuit-level representations, and \textbf{Causal Probing}, a do-calculus intervention method for identifying causal latent structures, enabling detection and correction of spurious correlations, demographic biases, and misaligned decision circuits during training. We further propose the \textbf{Cognitive Alignment Score (CAS)}, quantifying agreement between model-internal representations and human concepts, a \textbf{saliency-first privacy mechanism} sharing only thresholded attribution nodes, a bias-aware regularizer aligning subgroup statistics, and a Reveal-to-Revise loop integrating attribution signals into parameter updates without separate fine-tuning. Evaluated on CelebA, FairFace, Jigsaw, and HateXplain, our method achieves \textbf{94.1\%} accuracy, \textbf{92.3\%} macro F1, \textbf{79.4\%} IoU-XAI, and \textbf{12.7} FID at 72--76\% adversarial robustness, while reducing subgroup disparity $Δ_{\mathrm{bias}}$ by \textbf{41\%}, demonstrating that mechanistic interpretability, fairness, and generative performance can be jointly optimized.

The use of Artificial Intelligence (AI) models in real-world and high-risk applications has intensified the discussion about their trustworthiness and ethical usage, from both a technical and a legislative perspective. The field of eXplainable Artificial Intelligence (XAI) addresses this challenge by proposing explanations that bring to light the decision-making processes of complex black-box models. Despite being an essential property, the robustness of explanations is often an overlooked aspect during development: only robust explanation methods can increase the trust in the system as a whole. This paper investigates the role of robustness through the usage of a feature importance aggregation derived from multiple models ($k$-nearest neighbours, random forest and neural networks). Preliminary results showcase the potential in increasing the trustworthiness of the application, while leveraging multiple model's predictive power.

AI models are being increasingly integrated into real-world systems, raising significant concerns about their safety and security. Consequently, AI red teaming has become essential for organizations to proactively identify and address vulnerabilities before they can be exploited by adversaries. While numerous AI red teaming tools currently exist, practitioners face challenges in selecting the most appropriate tools from a rapidly expanding landscape, as well as managing complex and frequently conflicting software dependencies across isolated projects. Given these challenges and the relatively small number of organizations with dedicated AI red teams, there is a strong need to lower barriers to entry and establish a standardized environment that simplifies the setup and execution of comprehensive AI model assessments. Inspired by Kali Linux's role in traditional penetration testing, we introduce BlackIce, an open-source containerized toolkit designed for red teaming Large Language Models (LLMs) and classical machine learning (ML) models. BlackIce provides a reproducible, version-pinned Docker image that bundles 14 carefully selected open-source tools for Responsible AI and Security testing, all accessible via a unified command-line interface. With this setup, initiating red team assessments is as straightforward as launching a container, either locally or using a cloud platform. Additionally, the image's modular architecture facilitates community-driven extensions, allowing users to easily adapt or expand the toolkit as new threats emerge. In this paper, we describe the architecture of the container image, the process used for selecting tools, and the types of evaluations they support.

Sleep disorders have a major impact on patients' health and quality of life, but their diagnosis remains complex due to the diversity of symptoms. Today, technological advances, combined with medical data analysis, are opening new perspectives for a better understanding of these disorders. In particular, explainable artificial intelligence (XAI) aims to make AI model decisions understandable and interpretable for users. In this study, we propose a clustering-based method to group patients according to different sleep disorder profiles. By integrating an explainable approach, we identify the key factors influencing these pathologies. An experiment on anonymized real data illustrates the effectiveness and relevance of our approach.

Medical image segmentation annotation suffers from inter-rater variability (IRV) due to differences in annotators' expertise and the inherent blurriness of medical images. Standard approaches that simply average expert labels are flawed, as they discard the valuable clinical uncertainty revealed in disagreements. We introduce a fundamentally new approach with our group decision simulation framework, which works by mimicking the collaborative decision-making process of a clinical panel. Under this framework, an Expert Signature Generator (ESG) learns to represent individual annotator styles in a unique latent space. A Simulated Consultation Module (SCM) then intelligently generates the final segmentation by sampling from this space. This method achieved state-of-the-art results on challenging CBCT and MRI datasets (92.11% and 90.72% Dice scores). By treating expert disagreement as a useful signal instead of noise, our work provides a clear path toward more robust and trustworthy AI systems for healthcare.

The operationalization of ethics in the technical practices of artificial intelligence (AI) is facing significant challenges. To address the problem of ineffective implementation of AI ethics, we present our diagnosis, analysis, and interventional recommendations from a unique perspective of the real-world implementation of AI ethics through explainable AI (XAI) techniques. We first describe the phenomenon (i.e., the "symptoms") of ineffective implementation of AI ethics in explainable AI using four empirical cases. From the "symptoms", we diagnose the root cause (i.e., the "disease") being the dysfunction and imbalance of power structures in the sociotechnical system of AI. The power structures are dominated by unjust and unchecked power that does not represent the benefits and interests of the public and the most impacted communities, and cannot be countervailed by ethical power. Based on the understanding of power mechanisms, we propose three interventional recommendations to tackle the root cause, including: 1) Making power explicable and checked, 2) Reframing the narratives and assumptions of AI and AI ethics to check unjust power and reflect the values and benefits of the public, and 3) Uniting the efforts of ethical and scientific conduct of AI to encode ethical values as technical standards, norms, and methods, including conducting critical examinations and limitation analyses of AI technical practices. We hope that our diagnosis and interventional recommendations can be a useful input to the AI community and civil society's ongoing discussion and implementation of ethics in AI for ethical and responsible AI practice.

Artificial intelligence (AI) is rapidly transforming power electronics, with AI-related publications in IEEE Power Electronics Society selected journals increasing more than fourfold from 2020 to 2025. However, the ethical dimensions of this transformation have received limited attention. This article underscores the urgent need for an ethical framework to guide responsible AI integration in power electronics, not only to prevent AI-related incidents but also to comply with legal and regulatory responsibilities. In this context, this article identifies four core pillars of AI ethics in power electronics: Security & Safety, Explainability & Transparency, Energy Sustainability, and Evolving Roles of Engineers. Each pillar is supported by practical and actionable insights to ensure that ethical principles are embedded in algorithm design, system deployment, and the preparation of an AI-ready engineering workforce. The authors advocate for power electronics engineers to lead the ethical discourse, given their deep technical understanding of both AI systems and power conversion technologies. The paper concludes by calling on the IEEE Power Electronics Society to spearhead the establishment of ethical standards, talent development initiatives, and best practices that ensure AI innovations are not only technically advanced but also oriented toward human and societal benefit.

Demystifying Deep Learning-based Brain Tumor Segmentation with 3D UNets and Explainable AI (XAI): A Comparative Analysis

Ming Jie Ong, Sze Yinn Ung, Sim Kuan Goh +1

The current study investigated the use of Explainable Artificial Intelligence (XAI) to improve the accuracy of brain tumor segmentation in MRI images, with the goal of assisting physicians in clinical decision-making. The study focused on applying UNet models for brain tumor segmentation and using the XAI techniques of Gradient-weighted Class Activation Mapping (Grad-CAM) and attention-based visualization to enhance the understanding of these models. Three deep learning models - UNet, Residual UNet (ResUNet), and Attention UNet (AttUNet) - were evaluated to identify the best-performing model. XAI was employed with the aims of clarifying model decisions and increasing physicians' trust in these models. We compared the performance of two UNet variants (ResUNet and AttUNet) with the conventional UNet in segmenting brain tumors from the BraTS2020 public dataset and analyzed model predictions with Grad-CAM and attention-based visualization. Using the latest computer hardware, we trained and validated each model using the Adam optimizer and assessed their performance with respect to: (i) training, validation, and inference times, (ii) segmentation similarity coefficients and loss functions, and (iii) classification performance. Notably, during the final testing phase, ResUNet outperformed the other models with respect to Dice and Jaccard similarity scores, as well as accuracy, recall, and F1 scores. Grad-CAM provided visuospatial insights into the tumor subregions each UNet model focused on while attention-based visualization provided valuable insights into the working mechanisms of AttUNet's attention modules. These results demonstrated ResUNet as the best-performing model and we conclude by recommending its use for automated brain tumor segmentation in future clinical assessments. Our source code and checkpoint are available at https://github.com/ethanong98/MultiModel-XAI-Brats2020

This paper presents a framework for provably fair AI that overcomes the limits of current bias mitigation methods by systematically removing all sensitive information and its proxies. Using ontology engineering in OWL 2 QL, it formally defines sensitive attributes and infers their proxies through logical reasoning, constructing a sigma algebra G that captures the full structure of biased patterns. Fair representations are then obtained via Delbaen Majumdar optimal transport, which generates variables independent of G while minimizing L2 distance to preserve accuracy. This guarantees true independence rather than mere decorrelation. By modeling bias as dependence between sigma algebras, compiling ontological knowledge into measurable structures, and using optimal transport as the unique fair transformation, the approach ensures complete fairness in tasks like loan approval, where proxies such as ZIP code reveal race. The result is a certifiable and mathematically grounded method for trustworthy AI.