Research Papers

SHAP scores fail pervasively even when Lipschitz succeeds

Olivier Letoffe, Xuanxiang Huang, Joao Marques-Silva

The ubiquitous use of Shapley values in eXplainable AI (XAI) has been triggered by the tool SHAP, and as a result are commonly referred to as SHAP scores. Recent work devised examples of machine learning (ML) classifiers for which the computed SHAP scores are thoroughly unsatisfactory, by allowing human decision-makers to be misled. Nevertheless, such examples could be perceived as somewhat artificial, since the selected classes must be interpreted as numeric. Furthermore, it was unclear how general were the issues identified with SHAP scores. This paper answers these criticisms. First, the paper shows that for Boolean classifiers there are arbitrarily many examples for which the SHAP scores must be deemed unsatisfactory. Second, the paper shows that the issues with SHAP scores are also observed in the case of regression models. In addition, the paper studies the class of regression models that respect Lipschitz continuity, a measure of a function's rate of change that finds important recent uses in ML, including model robustness. Concretely, the paper shows that the issues with SHAP scores occur even for regression models that respect Lipschitz continuity. Finally, the paper shows that the same issues are guaranteed to exist for arbitrarily differentiable regression models.

Stress is a pervasive global health issue that can lead to severe mental health problems. Early detection offers timely intervention and prevention of stress-related disorders. The current early detection models perform "black box" inference suffering from limited explainability and trust which blocks the real-world clinical application. Thanks to the generative properties introduced by the Large Language Models (LLMs), the decision and the prediction from such models are semi-interpretable through the corresponding description. However, the existing LLMs are mostly trained for general purposes without the guidance of psychological cognitive theory. To this end, we first highlight the importance of prior theory with the observation of performance boosted by the chain-of-thoughts tailored for stress detection. This method termed Cognition Chain explicates the generation of stress through a step-by-step cognitive perspective based on cognitive appraisal theory with a progress pipeline: Stimulus $\rightarrow$ Evaluation $\rightarrow$ Reaction $\rightarrow$ Stress State, guiding LLMs to provide comprehensive reasoning explanations. We further study the benefits brought by the proposed Cognition Chain format by utilising it as a synthetic dataset generation template for LLMs instruction-tuning and introduce CogInstruct, an instruction-tuning dataset for stress detection. This dataset is developed using a three-stage self-reflective annotation pipeline that enables LLMs to autonomously generate and refine instructional data. By instruction-tuning Llama3 with CogInstruct, we develop CogLLM, an explainable stress detection model. Evaluations demonstrate that CogLLM achieves outstanding performance while enhancing explainability. Our work contributes a novel approach by integrating cognitive theories into LLM reasoning processes, offering a promising direction for future explainable AI research.

The Generative AI Ethics Playbook

Jessie J. Smith, Wesley Hanwen Deng, William H. Smith +3

The Generative AI Ethics Playbook provides guidance for identifying and mitigating risks of machine learning systems across various domains, including natural language processing, computer vision, and generative AI. This playbook aims to assist practitioners in diagnosing potential harms that may arise during the design, development, and deployment of datasets and models. It offers concrete strategies and resources for mitigating these risks, to help minimize negative impacts on users and society. Drawing on current best practices in both research and ethical considerations, this playbook aims to serve as a comprehensive resource for AI/ML practitioners. The intended audience of this playbook includes machine learning researchers, engineers, and practitioners who are involved in the creation and implementation of generative and multimodal models (e.g., text-to-text, image-to-image, text-to-image, text-to-video). Specifically, we provide transparency/documentation checklists, topics of interest, common questions, examples of harms through case studies, and resources and strategies to mitigate harms throughout the Generative AI lifecycle. This playbook was made collaboratively over the course of 16 months through extensive literature review of over 100 resources and peer-reviewed articles, as well as through an initial group brainstorming session with 18 interdisciplinary AI ethics experts from industry and academia, and with additional feedback from 8 experts (5 of whom were in the initial brainstorming session). We note that while this playbook provides examples, discussion, and harm mitigation strategies, research in this area is ongoing. Our playbook aims to be a practically useful survey, taking a high-level view rather than aiming for covering the entire existing body of research.

The advancement of AI technologies has greatly increased the complexity of AI pipelines as they include many stages such as data collection, pre-processing, training, evaluation and visualisation. To provide effective and accessible AI solutions, it is important to design pipelines for different user groups such as experts, professionals from different fields and laypeople. Ease of use and trust play a central role in the acceptance of AI systems. The presented system, ALPACA (Adaptive Learning Pipeline for Advanced Comprehensive AI Analysis), offers a comprehensive AI pipeline that addresses the needs of diverse user groups. ALPACA integrates visual and code-based development and facilitates all key phases of the AI pipeline. Its architecture is based on Celery (with Redis backend) for efficient task management, MongoDB for seamless data storage and Kubernetes for cloud-based scalability and resource utilisation. Future versions of ALPACA will support modern techniques such as federated and continuous learning as well as explainable AI methods to further improve security, usability and trustworthiness. The application is demonstrated by an Android app for similarity recognition, which emphasises ALPACA's potential for use in everyday life.

The issue of hallucinations in large language models (LLMs) remains a critical barrier to the adoption of AI in enterprise and other high-stakes applications. Despite advancements in retrieval-augmented generation (RAG) systems, current state-of-the-art methods fail to achieve more than 80% accuracy in generating faithful and factually correct outputs, even when provided with relevant and accurate context. In this work, we introduce Acurai, a novel systematic approach that achieves 100% hallucination-free responses in LLMs by reformatting queries and context data prior to input. Leveraging a deep understanding of LLM internal representations, the importance of noun-phrase dominance, and the role of discrete functional units (DFUs), Acurai ensures alignment between input context and generated output. We validate this method using the RAGTruth corpus, demonstrating its ability to eliminate 100% hallucinations for both GPT-4 and GPT-3.5 Turbo. Acurai sets a new standard for achieving consistent, accurate, and faithful AI responses, marking a significant step forward in the development of trustworthy AI systems.

Large language models (LLMs) have revolutionized the field of natural language processing with their impressive reasoning and question-answering capabilities. However, these models are sometimes prone to generating credible-sounding but incorrect information, a phenomenon known as LLM hallucinations. Reliable uncertainty estimation in LLMs is essential for fostering trust in their generated responses and serves as a critical tool for the detection and prevention of erroneous or hallucinated outputs. To achieve reliable and well-calibrated uncertainty quantification in open-ended and free-form natural language generation, we propose an uncertainty-aware fine-tuning approach for LLMs. This approach enhances the model's ability to provide reliable uncertainty estimates without compromising accuracy, thereby guiding them to produce more trustworthy responses. We introduce a novel uncertainty-aware causal language modeling loss function, grounded in the principles of decision theory. Through rigorous evaluation on multiple free-form question-answering datasets and models, we demonstrate that our uncertainty-aware fine-tuning approach yields better calibrated uncertainty estimates in natural language generation tasks than fine-tuning with the standard causal language modeling loss. Furthermore, the experimental results show that the proposed method significantly improves the model's ability to detect hallucinations and identify out-of-domain prompts.

Reinforcement Learning (RL) enables autonomous aerial vehicles to adapt quickly and make efficient decisions, making it well-suited for dynamic urban air mobility operations. However, the lack of safety guarantees and transparency hinders the airworthiness certification of RL-based flight control systems, particularly in low-altitude urban environments with human presence. This paper proposes a trustworthy reinforcement learning algorithm that utilizes safe techniques to address the AI trustworthiness requirements for aviation safety, ensuring the transparent and certifiable deployment of RL in safety-critical aerial operations. Specifically, we proposed a Trustworthy Reinforcement learning Using Safe Techniques for UAV Pursuit (TRUST-UP), which consists of two key components: a safety filter constructed from Control Barrier Functions (CBFs) that transforms unsafe RL actions into provably safe flight commands, and a switching strategy that enhances feasibility while maintaining operational transparency. These components enable trustworthy AI deployment in urban airspace, satisfying technical robustness and transparency requirements for aviation certification. Simulation results demonstrate that TRUST-UP enables autonomous UAVs to safely navigate congested urban environments while maintaining human-interpretable decision logic. This work contributes toward certifiable and explainable AI frameworks for low-altitude aviation, addressing the critical need for trustworthy autonomous flight systems in future urban air mobility.

Reinforcement learning (RL) has demonstrated remarkable success in solving complex decision-making problems, yet its adoption in critical domains is hindered by the lack of interpretability in its decision-making processes. Existing explainable AI (xAI) approaches often fail to provide meaningful explanations for RL agents, particularly because they overlook the contrastive nature of human reasoning--answering "why this action instead of that one?". To address this gap, we propose a novel framework of contrastive learning to explain RL selected actions, named $\textbf{VisionMask}$. VisionMask is trained to generate explanations by explicitly contrasting the agent's chosen action with alternative actions in a given state using a self-supervised manner. We demonstrate the efficacy of our method through experiments across diverse RL environments, evaluating it in terms of faithfulness, robustness, and complexity. Our results show that VisionMask significantly improves human understanding of agent behavior while maintaining accuracy and fidelity. Furthermore, we present examples illustrating how VisionMask can be used for counterfactual analysis. This work bridges the gap between RL and xAI, paving the way for safer and more interpretable RL systems.

The increasing complexity of AI models, especially in deep learning, has raised concerns about transparency and accountability, particularly in high-stakes applications like medical diagnostics, where opaque models can undermine trust. Explainable Artificial Intelligence (XAI) aims to address these issues by providing clear, interpretable models. Among XAI techniques, Concept Bottleneck Models (CBMs) enhance transparency by using high-level semantic concepts. However, CBMs are vulnerable to concept-level backdoor attacks, which inject hidden triggers into these concepts, leading to undetectable anomalous behavior. To address this critical security gap, we introduce ConceptGuard, a novel defense framework specifically designed to protect CBMs from concept-level backdoor attacks. ConceptGuard employs a multi-stage approach, including concept clustering based on text distance measurements and a voting mechanism among classifiers trained on different concept subgroups, to isolate and mitigate potential triggers. Our contributions are threefold: (i) we present ConceptGuard as the first defense mechanism tailored for concept-level backdoor attacks in CBMs; (ii) we provide theoretical guarantees that ConceptGuard can effectively defend against such attacks within a certain trigger size threshold, ensuring robustness; and (iii) we demonstrate that ConceptGuard maintains the high performance and interpretability of CBMs, crucial for trustworthiness. Through comprehensive experiments and theoretical proofs, we show that ConceptGuard significantly enhances the security and trustworthiness of CBMs, paving the way for their secure deployment in critical applications.

Code Language Models (CLMs) have achieved tremendous progress in source code understanding and generation, leading to a significant increase in research interests focused on applying CLMs to real-world software engineering tasks in recent years. However, in realistic scenarios, CLMs are exposed to potential malicious adversaries, bringing risks to the confidentiality, integrity, and availability of CLM systems. Despite these risks, a comprehensive analysis of the security vulnerabilities of CLMs in the extremely adversarial environment has been lacking. To close this research gap, we categorize existing attack techniques into three types based on the CIA triad: poisoning attacks (integrity \& availability infringement), evasion attacks (integrity infringement), and privacy attacks (confidentiality infringement). We have collected so far the most comprehensive (79) papers related to adversarial machine learning for CLM from the research fields of artificial intelligence, computer security, and software engineering. Our analysis covers each type of risk, examining threat model categorization, attack techniques, and countermeasures, while also introducing novel perspectives on eXplainable AI (XAI) and exploring the interconnections between different risks. Finally, we identify current challenges and future research opportunities. This study aims to provide a comprehensive roadmap for both researchers and practitioners and pave the way towards more reliable CLMs for practical applications.

Intrusion detection has been a commonly adopted detective security measures to safeguard systems and networks from various threats. A robust intrusion detection system (IDS) can essentially mitigate threats by providing alerts. In networks based IDS, typically we deal with cyber threats like distributed denial of service (DDoS), spoofing, reconnaissance, brute-force, botnets, and so on. In order to detect these threats various machine learning (ML) and deep learning (DL) models have been proposed. However, one of the key challenges with these predictive approaches is the presence of false positive (FP) and false negative (FN) instances. This FPs and FNs within any black-box intrusion detection system (IDS) make the decision-making task of an analyst further complicated. In this paper, we propose an explainable artificial intelligence (XAI) based visual analysis approach using overlapping SHAP plots that presents the feature explanation to identify potential false positive and false negatives in IDS. Our approach can further provide guidance to security analysts for effective decision-making. We present case study with multiple publicly available network traffic datasets to showcase the efficacy of our approach for identifying false positive and false negative instances. Our use-case scenarios provide clear guidance for analysts on how to use the visual analysis approach for reliable course-of-actions against such threats.

Credit card fraud detection is a critical concern for financial institutions, intensified by the rise of contactless payment technologies. While deep learning models offer high accuracy, their lack of explainability poses significant challenges in financial settings. This paper explores the integration of fuzzy logic into Deep Symbolic Regression (DSR) to enhance both performance and explainability in fraud detection. We investigate the effectiveness of different fuzzy logic implications, specifically Łukasiewicz, Gödel, and Product, in handling the complexity and uncertainty of fraud detection datasets. Our analysis suggest that the Łukasiewicz implication achieves the highest F1-score and overall accuracy, while the Product implication offers a favorable balance between performance and explainability. Despite having a performance lower than state-of-the-art (SOTA) models due to information loss in data transformation, our approach provides novelty and insights into into integrating fuzzy logic into DSR for fraud detection, providing a comprehensive comparison between different implications and methods.