Research Papers

Semantic-based test generators are widely used to produce failure-inducing inputs for Deep Learning (DL) systems. They typically generate challenging test inputs by applying random perturbations to input semantic concepts until a failure is found or a timeout is reached. However, such randomness may hinder them from efficiently achieving their goal. This paper proposes XMutant, a technique that leverages explainable artificial intelligence (XAI) techniques to generate challenging test inputs. XMutant uses the local explanation of the input to inform the fuzz testing process and effectively guide it toward failures of the DL system under test. We evaluated different configurations of XMutant in triggering failures for different DL systems both for model-level (sentiment analysis, digit recognition) and system-level testing (advanced driving assistance). Our studies showed that XMutant enables more effective and efficient test generation by focusing on the most impactful parts of the input. XMutant generates up to 125% more failure-inducing inputs compared to an existing baseline, up to 7X faster. We also assessed the validity of these inputs, maintaining a validation rate above 89%, according to automated and human validators.

The rise of social media has significantly increased the prevalence of cyberbullying (CB), posing serious risks to both mental and physical well-being. Effective detection systems are essential for mitigating its impact. While several machine learning (ML) models have been developed, few incorporate victims' psychological, demographic, and behavioral factors alongside bullying comments to assess severity. In this study, we propose an AI model intregrating user-specific attributes, including psychological factors (self-esteem, anxiety, depression), online behavior (internet usage, disciplinary history), and demographic attributes (race, gender, ethnicity), along with social media comments. Additionally, we introduce a re-labeling technique that categorizes social media comments into three severity levels: Not Bullying, Mild Bullying, and Severe Bullying, considering user-specific factors.Our LSTM model is trained using 146 features, incorporating emotional, topical, and word2vec representations of social media comments as well as user-level attributes and it outperforms existing baseline models, achieving the highest accuracy of 98\% and an F1-score of 0.97. To identify key factors influencing the severity of cyberbullying, we employ explainable AI techniques (SHAP and LIME) to interpret the model's decision-making process. Our findings reveal that, beyond hate comments, victims belonging to specific racial and gender groups are more frequently targeted and exhibit higher incidences of depression, disciplinary issues, and low self-esteem. Additionally, individuals with a prior history of bullying are at a greater risk of becoming victims of cyberbullying.

Extracting and Understanding the Superficial Knowledge in Alignment

Runjin Chen, Gabriel Jacob Perin, Xuxi Chen +5

Alignment of large language models (LLMs) with human values and preferences, often achieved through fine-tuning based on human feedback, is essential for ensuring safe and responsible AI behaviors. However, the process typically requires substantial data and computation resources. Recent studies have revealed that alignment might be attainable at lower costs through simpler methods, such as in-context learning. This leads to the question: Is alignment predominantly superficial? In this paper, we delve into this question and provide a quantitative analysis. We formalize the concept of superficial knowledge, defining it as knowledge that can be acquired through easily token restyling, without affecting the model's ability to capture underlying causal relationships between tokens. We propose a method to extract and isolate superficial knowledge from aligned models, focusing on the shallow modifications to the final token selection process. By comparing models augmented only with superficial knowledge to fully aligned models, we quantify the superficial portion of alignment. Our findings reveal that while superficial knowledge constitutes a significant portion of alignment, particularly in safety and detoxification tasks, it is not the whole story. Tasks requiring reasoning and contextual understanding still rely on deeper knowledge. Additionally, we demonstrate two practical advantages of isolated superficial knowledge: (1) it can be transferred between models, enabling efficient offsite alignment of larger models using extracted superficial knowledge from smaller models, and (2) it is recoverable, allowing for the restoration of alignment in compromised models without sacrificing performance.

An Explainable Biomedical Foundation Model via Large-Scale Concept-Enhanced Vision-Language Pre-training

Yuxiang Nie, Sunan He, Yequan Bie +14

The clinical adoption of artificial intelligence (AI) in medical imaging requires models that are both diagnostically accurate and interpretable to clinicians. While current multimodal biomedical foundation models prioritize performance, their black-box nature hinders explaining the decision-making process in clinically meaningful concepts. Here, we present ConceptCLIP, the first explainable biomedical foundation model that achieves state-of-the-art diagnostic accuracy while delivering human-interpretable explanations across diverse imaging modalities. We curate MedConcept-23M, the largest pre-training dataset comprising 23 million image-text-concept triplets across diverse medical modalities, where clinical concepts are derived from the Unified Medical Language System. Leveraging this dataset, we develop ConceptCLIP through a novel dual-alignment approach that simultaneously learns global image-text representations and fine-grained region-concept associations for precise and interpretable medical image analysis. We curate the most extensive evaluation benchmark for multimodal biomedical foundation models, covering 52 clinical tasks spanning 10 imaging modalities. Extensive experiments demonstrate that ConceptCLIP outperforms existing state-of-the-art multimodal biomedical foundation models. Importantly, ConceptCLIP demonstrates superior diagnostic performance while providing human-understandable explanations validated by clinical experts. As the first precise and interpretable biomedical foundation model, ConceptCLIP represents a critical milestone toward the widespread clinical adoption of AI, thereby advancing trustworthy AI in medicine.

Skin cancer is one of the most prevalent and potentially life-threatening diseases worldwide, necessitating early and accurate diagnosis to improve patient outcomes. Conventional diagnostic methods, reliant on clinical expertise and histopathological analysis, are often time-intensive, subjective, and prone to variability. To address these limitations, we propose a novel hybrid deep learning framework that integrates convolutional neural networks (CNNs) with Radial Basis Function (RBF) Networks to achieve high classification accuracy and enhanced interpretability. The motivation for incorporating RBF Networks lies in their intrinsic interpretability and localized response to input features, which make them well-suited for tasks requiring transparency and fine-grained decision-making. Unlike traditional deep learning models that rely on global feature representations, RBF Networks allow for mapping segments of images to chosen prototypes, exploiting salient features within a single image. This enables clinicians to trace predictions to specific, interpretable patterns. The framework incorporates segmentation-based feature extraction, active learning for prototype selection, and K-Medoids clustering to focus on these salient features. Evaluations on the ISIC 2016 and ISIC 2017 datasets demonstrate the model's effectiveness, achieving classification accuracies of 83.02\% and 72.15\% using ResNet50, respectively, and outperforming VGG16-based configurations. By generating interpretable explanations for predictions, the framework aligns with clinical workflows, bridging the gap between predictive performance and trustworthiness. This study highlights the potential of hybrid models to deliver actionable insights, advancing the development of reliable AI-assisted diagnostic tools for high-stakes medical applications.

The FAPL-DM-BC solution is a new FL-based privacy, security, and scalability solution for the Internet of Vehicles (IoV). It leverages Federated Adaptive Privacy-Aware Learning (FAPL) and Dynamic Masking (DM) to learn and adaptively change privacy policies in response to changing data sensitivity and state in real-time, for the optimal privacy-utility tradeoff. Secure Logging and Verification, Blockchain-based provenance and decentralized validation, and Cloud Microservices Secure Aggregation using FedAvg (Federated Averaging) and Secure Multi-Party Computation (SMPC). Two-model feedback, driven by Model-Agnostic Explainable AI (XAI), certifies local predictions and explanations to drive it to the next level of efficiency. Combining local feedback with world knowledge through a weighted mean computation, FAPL-DM-BC assures federated learning that is secure, scalable, and interpretable. Self-driving cars, traffic management, and forecasting, vehicular network cybersecurity in real-time, and smart cities are a few possible applications of this integrated, privacy-safe, and high-performance IoV platform.

We investigate the connection between visual semantic features defined in PI-RADS and associated risk factors, moving beyond abnormal imaging findings, establishing a shared framework between medical and AI professionals by creating a standardized dictionary of biological/radiological RFs. Subsequently, 6 interpretable and seven complex classifiers, linked with nine interpretable feature selection algorithms (FSA) applied to risk factors, were extracted from segmented lesions in T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) multiparametric-prostate MRI sequences to predict the UCLA scores. We then utilized the created dictionary to interpret the best-predictive models. Combining T2WI, DWI, and ADC with FSAs including ANOVA F-test, Correlation Coefficient, and Fisher Score, and utilizing logistic regression, identified key features: The 90th percentile from T2WI, which captures hypo-intensity related to prostate cancer risk; Variance from T2WI, indicating lesion heterogeneity; shape metrics including Least Axis Length and Surface Area to Volume ratio from ADC, describing lesion shape and compactness; and Run Entropy from ADC, reflecting texture consistency. This approach achieved the highest average accuracy of 0.78, significantly outperforming single-sequence methods (p-value<0.05). The developed dictionary for Prostate-MRI (PM1.0) serves as a common language, fosters collaboration between clinical professionals and AI developers to advance trustworthy AI solutions that support reliable/interpretable clinical decisions.

Explainable Artificial Intelligence (XAI) methods are increasingly used in safety-critical domains, yet there is no unified framework to jointly evaluate fidelity, interpretability, robustness, fairness, and completeness. We address this gap through two contributions. First, we propose a multi-criteria evaluation framework that formalizes these five criteria using principled metrics: fidelity via prediction-gap analysis; interpretability via a composite concentration-coherence-contrast score; robustness via cosine-similarity perturbation stability; fairness via Jensen-Shannon divergence across demographic groups; and completeness via feature-ablation coverage. These are integrated using an entropy-weighted dynamic scoring scheme that adapts to domain-specific priorities. Second, we introduce Perturbation-Gradient Consensus Attribution (PGCA), which fuses grid-based perturbation importance with Grad-CAM++ through consensus amplification and adaptive contrast enhancement, combining perturbation fidelity with gradient-based spatial precision. We evaluate across five domains (brain tumor MRI, plant disease, security screening, gender, and sunglass detection) using fine-tuned ResNet-50 models. PGCA achieves the best performance in fidelity $(2.22 \pm 1.62)$, interpretability $(3.89 \pm 0.33)$, and fairness $(4.95 \pm 0.03)$, with statistically significant improvements over baselines $(p < 10^{-7})$. Sensitivity analysis shows stable rankings (Kendall's $(τ\geq 0.88)$). Code and results are publicly available.

Info-CELS: Informative Saliency Map Guided Counterfactual Explanation

Peiyu Li, Omar Bahri, Pouya Hosseinzadeh +2

As the demand for interpretable machine learning approaches continues to grow, there is an increasing necessity for human involvement in providing informative explanations for model decisions. This is necessary for building trust and transparency in AI-based systems, leading to the emergence of the Explainable Artificial Intelligence (XAI) field. Recently, a novel counterfactual explanation model, CELS, has been introduced. CELS learns a saliency map for the interest of an instance and generates a counterfactual explanation guided by the learned saliency map. While CELS represents the first attempt to exploit learned saliency maps not only to provide intuitive explanations for the reason behind the decision made by the time series classifier but also to explore post hoc counterfactual explanations, it exhibits limitations in terms of high validity for the sake of ensuring high proximity and sparsity. In this paper, we present an enhanced approach that builds upon CELS. While the original model achieved promising results in terms of sparsity and proximity, it faced limitations in validity. Our proposed method addresses this limitation by removing mask normalization to provide more informative and valid counterfactual explanations. Through extensive experimentation on datasets from various domains, we demonstrate that our approach outperforms the CELS model, achieving higher validity and producing more informative explanations.

Medical image classification is crucial for supporting healthcare professionals in decision-making and training. While Convolutional Neural Networks (CNNs) have traditionally dominated this field, Transformer-based models are gaining attention. In this study, we apply explainable AI (XAI) techniques to assess the performance of various models on real-world medical data and identify areas for improvement. We compare CNN models such as VGG-16, ResNet-50, and EfficientNetV2L with a Transformer model: ViT-Base-16. Our results show that data augmentation has little impact, but hyperparameter tuning and advanced modeling improve performance. CNNs, particularly VGG-16 and ResNet-50, outperform ViT-Base-16 and EfficientNetV2L, likely due to underfitting from limited data. XAI methods like LIME and SHAP further reveal that better-performing models visualize tumors more effectively. These findings suggest that CNNs with shallower architectures are more effective for small datasets and can support medical decision-making.

When performing predictions that use Machine Learning (ML), we are mainly interested in performance and interpretability. This generates a natural trade-off, where complex models generally have higher skills but are harder to explain and thus trust. Interpretability is particularly important in the climate community, where we aim at gaining a physical understanding of the underlying phenomena. Even more so when the prediction concerns extreme weather events with high impact on society. In this paper, we perform probabilistic forecasts of extreme heatwaves over France, using a hierarchy of increasingly complex ML models, which allows us to find the best compromise between accuracy and interpretability. More precisely, we use models that range from a global Gaussian Approximation (GA) to deep Convolutional Neural Networks (CNNs), with the intermediate steps of a simple Intrinsically Interpretable Neural Network (IINN) and a model using the Scattering Transform (ScatNet). Our findings reveal that CNNs provide higher accuracy, but their black-box nature severely limits interpretability, even when using state-of-the-art Explainable Artificial Intelligence (XAI) tools. In contrast, ScatNet achieves similar performance to CNNs while providing greater transparency, identifying key scales and patterns in the data that drive predictions. This study underscores the potential of interpretability in ML models for climate science, demonstrating that simpler models can rival the performance of their more complex counterparts, all the while being much easier to understand. This gained interpretability is crucial for building trust in model predictions and uncovering new scientific insights, ultimately advancing our understanding and management of extreme weather events.

Convolutional neural networks (CNNs) achieve prevailing results in segmentation tasks nowadays and represent the state-of-the-art for image-based analysis. However, the understanding of the accurate decision-making process of a CNN is rather unknown. The research area of explainable artificial intelligence (xAI) primarily revolves around understanding and interpreting this black-box behavior. One way of interpreting a CNN is the use of class activation maps (CAMs) that represent heatmaps to indicate the importance of image areas for the prediction of the CNN. For classification tasks, a variety of CAM algorithms exist. But for segmentation tasks, only one CAM algorithm for the interpretation of the output of a CNN exist. We propose a transfer between existing classification- and segmentation-based methods for more detailed, explainable, and consistent results which show salient pixels in semantic segmentation tasks. The resulting Seg-HiRes-Grad CAM is an extension of the segmentation-based Seg-Grad CAM with the transfer to the classification-based HiRes CAM. Our method improves the previously-mentioned existing segmentation-based method by adjusting it to recently published classification-based methods. Especially for medical image segmentation, this transfer solves existing explainability disadvantages.