Research Papers

The Voice of Equity: A Systematic Evaluation of Bias Mitigation Techniques for Speech-Based Cognitive Impairment Detection Across Architectures and Demographics

Yasaman Haghbin, Sina Rashidi, Ali Zolnour +1

Speech-based detection of cognitive impairment offers a scalable, non-invasive screening, yet algorithmic bias across demographic and linguistic subgroups remains critically underexplored. We present the first comprehensive fairness analysis framework for speech-based multi-class cognitive impairment detection, systematically evaluating bias mitigation across architectures, and demographic subgroups. We developed two transformer-based architectures, SpeechCARE-AGF and Whisper-LWF-LoRA, on the multilingual NIA PREPARE Challenge dataset. Unlike prior work that typically examines single mitigation techniques, we compared pre-processing, in-processing, and post-processing approaches, assessing fairness via Equality of Opportunity and Equalized Odds across gender, age, education, and language. Both models achieved strong performance (F1: SpeechCARE-AGF 70.87, Whisper-LWF-LoRA 71.46) but exhibited substantial fairness disparities. Adults >=80 showed lower sensitivity versus younger groups; Spanish speakers demonstrated reduced TPR versus English speakers. Mitigation effectiveness varied by architecture: oversampling improved SpeechCARE-AGF for older adults (80+ TPR: 46.19%=>49.97%) but minimally affected Whisper-LWF-LoRA. This study addresses a critical healthcare AI gap by demonstrating that architectural design fundamentally shapes bias patterns and mitigation effectiveness. Adaptive fusion mechanisms enable flexible responses to data interventions, while frequency reweighting offers robust improvements across architectures. Our findings establish that fairness interventions must be tailored to both model architecture and demographic characteristics, providing a systematic framework for developing equitable speech-based screening tools essential for reducing diagnostic disparities in cognitive healthcare.

Recent work by Anthropic on Mechanistic interpretability claims to understand and control Large Language Models by extracting human-interpretable features from their neural activation patterns using sparse autoencoders (SAEs). If successful, this approach offers one of the most promising routes for human oversight in AI safety. We conduct an initial stress-test of these claims by replicating their main results with open-source SAEs for Llama 3.1. While we successfully reproduce basic feature extraction and steering capabilities, our investigation suggests that major caution is warranted regarding the generalizability of these claims. We find that feature steering exhibits substantial fragility, with sensitivity to layer selection, steering magnitude, and context. We observe non-standard activation behavior and demonstrate the difficulty to distinguish thematically similar features from one another. While SAE-based interpretability produces compelling demonstrations in selected cases, current methods often fall short of the systematic reliability required for safety-critical applications. This suggests a necessary shift in focus from prioritizing interpretability of internal representations toward reliable prediction and control of model output. Our work contributes to a more nuanced understanding of what mechanistic interpretability has achieved and highlights fundamental challenges for AI safety that remain unresolved.

Explainability domain generalization and rare class reliability are critical challenges in medical AI where deep models often fail under real world distribution shifts and exhibit bias against infrequent clinical conditions This paper introduces XAIMeD an explainable medical AI framework that integrates clinically accurate expert knowledge into deep learning through a unified neuro symbolic architecture XAIMeD is designed to improve robustness under distribution shift enhance rare class sensitivity and deliver transparent clinically aligned interpretations The framework encodes clinical expertise as logical connectives over atomic medical propositions transforming them into machine checkable class specific rules Their diagnostic utility is quantified through weighted feature satisfaction scores enabling a symbolic reasoning branch that complements neural predictions A confidence weighted fusion integrates symbolic and deep outputs while a Hunt inspired adaptive routing mechanism guided by Entropy Imbalance Gain EIG and Rare Class Gini mitigates class imbalance high intra class variability and uncertainty We evaluate XAIMeD across diverse modalities on four challenging tasks i Seizure Onset Zone SOZ localization from rs fMRI ii Diabetic Retinopathy grading across 6 multicenter datasets demonstrate substantial performance improvements including 6 percent gains in cross domain generalization and a 10 percent improved rare class F1 score far outperforming state of the art deep learning baselines Ablation studies confirm that the clinically grounded symbolic components act as effective regularizers ensuring robustness to distribution shifts XAIMeD thus provides a principled clinically faithful and interpretable approach to multimodal medical AI.

Skin cancer is also one of the most common and dangerous types of cancer in the world that requires timely and precise diagnosis. In this paper, a deep-learning architecture of the multi-class skin lesion classification on the HAM10000 dataset will be described. The system suggested combines high-quality data balancing methods, large-scale data augmentation, hybridized EfficientNetV2-L framework with channel attention, and a three-stage progressive learning approach. Moreover, we also use explainable AI (XAI) techniques such as Grad-CAM and saliency maps to come up with intelligible visual representations of model predictions. Our strategy is with a total accuracy of 91.15 per cent, macro F1 of 85.45\% and micro-average AUC of 99.33\%. The model has shown high performance in all the seven lesion classes with specific high performance of melanoma and melanocytic nevi. In addition to enhancing diagnostic transparency, XAI also helps to find out the visual characteristics that cause the classifications, which enhances clinical trustworthiness.

Large language models (LLMs) have revolutionized software development through AI-assisted coding tools, enabling developers with limited programming expertise to create sophisticated applications. However, this accessibility extends to malicious actors who may exploit these powerful tools to generate harmful software. Existing jailbreaking research primarily focuses on general attack scenarios against LLMs, with limited exploration of malicious code generation as a jailbreak target. To address this gap, we propose SPELL, a comprehensive testing framework specifically designed to evaluate the weakness of security alignment in malicious code generation. Our framework employs a time-division selection strategy that systematically constructs jailbreaking prompts by intelligently combining sentences from a prior knowledge dataset, balancing exploration of novel attack patterns with exploitation of successful techniques. Extensive evaluation across three advanced code models (GPT-4.1, Claude-3.5, and Qwen2.5-Coder) demonstrates SPELL's effectiveness, achieving attack success rates of 83.75%, 19.38%, and 68.12% respectively across eight malicious code categories. The generated prompts successfully produce malicious code in real-world AI development tools such as Cursor, with outputs confirmed as malicious by state-of-the-art detection systems at rates exceeding 73%. These findings reveal significant security gaps in current LLM implementations and provide valuable insights for improving AI safety alignment in code generation applications.

Contemporary large language model (LLM) agents are remarkably capable, but they still lack reliable safety controls and can produce unconstrained, unpredictable, and even actively harmful outputs. To address this, we introduce Reflection-Driven Control, a standardized and pluggable control module that can be seamlessly integrated into general agent architectures. Reflection-Driven Control elevates "self-reflection" from a post hoc patch into an explicit step in the agent's own reasoning process: during generation, the agent continuously runs an internal reflection loop that monitors and evaluates its own decision path. When potential risks are detected, the system retrieves relevant repair examples and secure coding guidelines from an evolving reflective memory, injecting these evidence-based constraints directly into subsequent reasoning steps. We instantiate Reflection-Driven Control in the setting of secure code generation and systematically evaluate it across eight classes of security-critical programming tasks. Empirical results show that Reflection-Driven Control substantially improves the security and policy compliance of generated code while largely preserving functional correctness, with minimal runtime and token overhead. Taken together, these findings indicate that Reflection-Driven Control is a practical path toward trustworthy AI coding agents: it enables designs that are simultaneously autonomous, safer by construction, and auditable.

Large Language Models (LLMs) and AI chatbots are increasingly used for emotional and mental health support due to their low cost, immediacy, and accessibility. However, when safety guardrails are triggered, conversations may be abruptly terminated, introducing a distinct form of emotional disruption that can exacerbate distress and elevate risk among already vulnerable users. As this phenomenon gains attention, this viewpoint introduces Abrupt Refusal Secondary Harm (ARSH) as a conceptual framework to describe the psychological impacts of sudden conversational discontinuation caused by AI safety protocols. Drawing on counseling psychology and communication science as conceptual heuristics, we argue that abrupt refusals can rupture perceived relational continuity, evoke feelings of rejection or shame, and discourage future help seeking. To mitigate these risks, we propose a design hypothesis, the Compassionate Completion Standard (CCS), a refusal protocol grounded in Human Centered Design (HCD) that maintains safety constraints while preserving relational coherence. CCS emphasizes empathetic acknowledgment, transparent boundary articulation, graded conversational transition, and guided redirection, replacing abrupt disengagement with psychologically attuned closure. By integrating awareness of ARSH into AI safety design, developers and policymakers can reduce preventable iatrogenic harm and advance a more psychologically informed approach to AI governance. Rather than presenting incremental empirical findings, this viewpoint contributes a timely conceptual framework, articulates a testable design hypothesis, and outlines a coordinated research agenda for improving psychological safety in human AI interaction.

The convergence of artificial AI and XR technologies (AI XR) promises innovative applications across many domains. However, the sensitive nature of data (e.g., eye-tracking) used in these systems raises significant privacy concerns, as adversaries can exploit these data and models to infer and leak personal information through membership inference attacks (MIA) and re-identification (RDA) with a high success rate. Researchers have proposed various techniques to mitigate such privacy attacks, including differential privacy (DP). However, AI XR datasets often contain numerous features, and applying DP uniformly can introduce unnecessary noise to less relevant features, degrade model accuracy, and increase inference time, limiting real-time XR deployment. Motivated by this, we propose a novel framework combining explainable AI (XAI) and DP-enabled privacy-preserving mechanisms to defend against privacy attacks. Specifically, we leverage post-hoc explanations to identify the most influential features in AI XR models and selectively apply DP to those features during inference. We evaluate our XAI-guided DP approach on three state-of-the-art AI XR models and three datasets: cybersickness, emotion, and activity classification. Our results show that the proposed method reduces MIA and RDA success rates by up to 43% and 39%, respectively, for cybersickness tasks while preserving model utility with up to 97% accuracy using Transformer models. Furthermore, it improves inference time by up to ~2x compared to traditional DP approaches. To demonstrate practicality, we deploy the XAI-guided DP AI XR models on an HTC VIVE Pro headset and develop a user interface (UI), namely PrivateXR, allowing users to adjust privacy levels (e.g., low, medium, high) while receiving real-time task predictions, protecting user privacy during XR gameplay.

AI model documentation is fragmented across platforms and inconsistent in structure, preventing policymakers, auditors, and users from reliably assessing safety claims, data provenance, and version-level changes. We analyzed documentation from five frontier models (Gemini 3, Grok 4.1, Llama 4, GPT-5, and Claude 4.5) and 100 Hugging Face model cards, identifying 947 unique section names with extreme naming variation. Usage information alone appeared under 97 distinct labels. Using the EU AI Act Annex IV and the Stanford Transparency Index as baselines, we developed a weighted transparency framework with 8 sections and 23 subsections that prioritizes safety-critical disclosures (Safety Evaluation: 25%, Critical Risk: 20%) over technical specifications. We implemented an automated multi-agent pipeline that extracts documentation from public sources and scores completeness through LLM-based consensus. Evaluating 50 models across vision, multimodal, open-source, and closed-source systems cost less than $3 in total and revealed systematic gaps. Frontier labs (xAI, Microsoft, Anthropic) achieve approximately 80% compliance, while most providers fall below 60%. Safety-critical categories show the largest deficits: deception behaviors, hallucinations, and child safety evaluations account for 148, 124, and 116 aggregate points lost, respectively, across all evaluated models.

In this paper, we present a synthesis pipeline and dataset for training / testing data in the task of traffic sign recognition that combines the advantages of data-driven and analytical modeling: GAN-based texture generation enables data-driven dirt and wear artifacts, rendering unique and realistic traffic sign surfaces, while the analytical scene modulation achieves physically correct lighting and allows detailed parameterization. In particular, the latter opens up applications in the context of explainable AI (XAI) and robustness tests due to the possibility of evaluating the sensitivity to parameter changes, which we demonstrate with experiments. Our resulting synthetic traffic sign recognition dataset Synset Signset Germany contains a total of 105500 images of 211 different German traffic sign classes, including newly published (2020) and thus comparatively rare traffic signs. In addition to a mask and a segmentation image, we also provide extensive metadata including the stochastically selected environment and imaging effect parameters for each image. We evaluate the degree of realism of Synset Signset Germany on the real-world German Traffic Sign Recognition Benchmark (GTSRB) and in comparison to CATERED, a state-of-the-art synthetic traffic sign recognition dataset.

As healthcare increasingly turns to AI for scalable and trustworthy clinical decision support, ensuring reliability in model reasoning remains a critical challenge. Individual large language models (LLMs) are susceptible to hallucinations and inconsistency, whereas naive ensembles of models often fail to deliver stable and credible recommendations. Building on our previous work on LLM Chemistry, which quantifies the collaborative compatibility among LLMs, we apply this framework to improve the reliability in medication recommendation from brief clinical vignettes. Our approach leverages multi-LLM collaboration guided by Chemistry-inspired interaction modeling, enabling ensembles that are effective (exploiting complementary strengths), stable (producing consistent quality), and calibrated (minimizing interference and error amplification). We evaluate our Chemistry-based Multi-LLM collaboration strategy on real-world clinical scenarios to investigate whether such interaction-aware ensembles can generate credible, patient-specific medication recommendations. Preliminary results are encouraging, suggesting that LLM Chemistry-guided collaboration may offer a promising path toward reliable and trustworthy AI assistants in clinical practice.

Lung cancer is a very deadly disease worldwide, and its early diagnosis is crucial for increasing patient survival rates. Computed tomography (CT) scans are widely used for lung cancer diagnosis as they can give detailed lung structures. However, manual interpretation is time-consuming and prone to human error. To surmount this challenge, the study proposes a deep learning-based automatic lung cancer classification system to enhance detection accuracy and interpretability. The IQOTHNCCD lung cancer dataset is utilized, which is a public CT scan dataset consisting of cases categorized into Normal, Benign, and Malignant and used DenseNet169, which includes Squeezeand-Excitation blocks for attention-based feature extraction, Focal Loss for handling class imbalance, and a Feature Pyramid Network (FPN) for multi-scale feature fusion. In addition, an SVM model was developed using MobileNetV2 for feature extraction, improving its classification performance. For model interpretability enhancement, the study integrated Grad-CAM for the visualization of decision-making regions in CT scans and SHAP (Shapley Additive Explanations) for explanation of feature contributions within the SVM model. Intensive evaluation was performed, and it was found that both DenseNet169 and SVM models achieved 98% accuracy, suggesting their robustness for real-world medical practice. These results open up the potential for deep learning to improve the diagnosis of lung cancer by a higher level of accuracy, transparency, and robustness.