Research Papers

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.

Due to the susceptibility of Artificial Intelligence (AI) to data perturbations and adversarial examples, it is crucial to perform a thorough robustness evaluation before any Machine Learning (ML) model is deployed. However, examining a model's decision boundaries and identifying potential vulnerabilities typically requires access to the training and testing datasets, which may pose risks to data privacy and confidentiality. To improve transparency in organizations that handle confidential data or manage critical infrastructure, it is essential to allow external verification and validation of AI without the disclosure of private datasets. This paper presents Systematic Pattern Analysis (SPATA), a deterministic method that converts any tabular dataset to a domain-independent representation of its statistical patterns, to provide more detailed and transparent data cards. SPATA computes the projection of each data instance into a discrete space where they can be analyzed and compared, without risking data leakage. These projected datasets can be reliably used for the evaluation of how different features affect ML model robustness and for the generation of interpretable explanations of their behavior, contributing to more trustworthy AI.

Artificial Intelligence (AI) systems introduce unprecedented privacy challenges as they process increasingly sensitive data. Traditional privacy frameworks prove inadequate for AI technologies due to unique characteristics such as autonomous learning and black-box decision-making. This paper presents a taxonomy classifying AI privacy risks, synthesised from 45 studies identified through systematic review. We identify 19 key risks grouped under four categories: Dataset-Level, Model-Level, Infrastructure-Level, and Insider Threat Risks. Findings reveal a balanced distribution across these dimensions, with human error (9.45%) emerging as the most significant factor. This taxonomy challenges conventional security approaches that typically prioritise technical controls over human factors, highlighting gaps in holistic understanding. By bridging technical and behavioural dimensions of AI privacy, this paper contributes to advancing trustworthy AI development and provides a foundation for future research.

Backdoor attacks pose a significant security threat to natural language processing (NLP) systems, but existing methods lack explainable trigger mechanisms and fail to quantitatively model vulnerability patterns. This work pioneers the quantitative connection between explainable artificial intelligence (XAI) and backdoor attacks, introducing Sensitron, a novel modular framework for crafting stealthy and robust backdoor triggers. Sensitron employs a progressive refinement approach where Dynamic Meta-Sensitivity Analysis (DMSA) first identifies potentially vulnerable input tokens, Hierarchical SHAP Estimation (H-SHAP) then provides explainable attribution to precisely pinpoint the most influential tokens, and finally a Plug-and-Rank mechanism that generates contextually appropriate triggers. We establish the first mathematical correlation (Sensitivity Ranking Correlation, SRC=0.83) between explainability scores and empirical attack success, enabling precise targeting of model vulnerabilities. Sensitron achieves 97.8% Attack Success Rate (ASR) (+5.8% over state-of-the-art (SOTA)) with 85.4% ASR at 0.1% poisoning rate, demonstrating robust resistance against multiple SOTA defenses. This work reveals fundamental NLP vulnerabilities and provides new attack vectors through weaponized explainability.

As smart tourism evolves, AI-powered chatbots have become indispensable for delivering personalized, real-time assistance to travelers while promoting sustainability and efficiency. However, these systems are increasingly vulnerable to prompt injection attacks, where adversaries manipulate inputs to elicit unintended behaviors such as leaking sensitive information or generating harmful content. This paper presents a case study on the design and implementation of a secure retrieval-augmented generation (RAG) chatbot for Hsinchu smart tourism services. The system integrates RAG with API function calls, multi-layered linguistic analysis, and guardrails against injections, achieving high contextual awareness and security. Key features include a tiered response strategy, RAG-driven knowledge grounding, and intent decomposition across lexical, semantic, and pragmatic levels. Defense mechanisms include system norms, gatekeepers for intent judgment, and reverse RAG text to prioritize verified data. We also benchmark a GPT-5 variant (released 2025-08-07) to assess inherent robustness. Evaluations with 674 adversarial prompts and 223 benign queries show over 95% accuracy on benign tasks and substantial detection of injection attacks. GPT-5 blocked about 85% of attacks, showing progress yet highlighting the need for layered defenses. Findings emphasize contributions to sustainable tourism, multilingual accessibility, and ethical AI deployment. This work offers a practical framework for deploying secure chatbots in smart tourism and contributes to resilient, trustworthy AI applications.

The classification of network traffic using machine learning (ML) models is one of the primary mechanisms to address the security issues in IoT networks and/or IoT devices. However, the ML models often act as black-boxes that create a roadblock to take critical decision based on the model output. To address this problem, we design and develop a system, called rCamInspector, that employs Explainable AI (XAI) to provide reliable and trustworthy explanations to model output. rCamInspector adopts two classifiers, Flow Classifier - categorizes a flow into one of four classes, IoTCam, Conf, Share and Others, and SmartCam Classifier - classifies an IoTCam flow into one of six classes, Netatmo, Spy Clock, Canary, D3D, Ezviz, V380 Spy Bulb; both are IP address and transport port agnostic. rCamInspector is evaluated using 38GB of network traffic and our results show that XGB achieves the highest accuracy of 92% and 99% in the Flow and SmartCam classifiers respectively among eight supervised ML models. We analytically show that the traditional mutual information (MI) based feature importance cannot provide enough reliability on the model output of XGB in either classifiers. Using SHAP and LIME, we show that a separate set of features can be picked up to explain a correct prediction of XGB. For example, the feature Init Bwd Win Byts turns out to have the highest SHAP values to support the correct prediction of both IoTCam in Flow Classifier and Netatmo class in SmartCam Classifier. To evaluate the faithfulness of the explainers on our dataset, we show that both SHAP and LIME have a consistency of more than 0.7 and a sufficiency of 1.0. Comparing with existing works, we show that rCamInspector achieves a better accuracy (99%), precision (99%), and false negative rate (0.7%).

EPT Benchmark: Evaluation of Persian Trustworthiness in Large Language Models

Mohammad Reza Mirbagheri, Mohammad Mahdi Mirkamali, Zahra Motoshaker Arani +3

Large Language Models (LLMs), trained on extensive datasets using advanced deep learning architectures, have demonstrated remarkable performance across a wide range of language tasks, becoming a cornerstone of modern AI technologies. However, ensuring their trustworthiness remains a critical challenge, as reliability is essential not only for accurate performance but also for upholding ethical, cultural, and social values. Careful alignment of training data and culturally grounded evaluation criteria are vital for developing responsible AI systems. In this study, we introduce the EPT (Evaluation of Persian Trustworthiness) metric, a culturally informed benchmark specifically designed to assess the trustworthiness of LLMs across six key aspects: truthfulness, safety, fairness, robustness, privacy, and ethical alignment. We curated a labeled dataset and evaluated the performance of several leading models - including ChatGPT, Claude, DeepSeek, Gemini, Grok, LLaMA, Mistral, and Qwen - using both automated LLM-based and human assessments. Our results reveal significant deficiencies in the safety dimension, underscoring the urgent need for focused attention on this critical aspect of model behavior. Furthermore, our findings offer valuable insights into the alignment of these models with Persian ethical-cultural values and highlight critical gaps and opportunities for advancing trustworthy and culturally responsible AI. The dataset is publicly available at: https://github.com/Rezamirbagheri110/EPT-Benchmark.

It is known that big data analytics and AI pose a threat to privacy, and that some of this is due to some kind of "black box problem" in AI. I explain how this becomes a problem in the context of justification for judgments and actions. Furthermore, I suggest distinguishing three kinds of opacity: 1) the subjects do not know what the system does ("shallow opacity"), 2) the analysts do not know what the system does ("standard black box opacity"), or 3) the analysts cannot possibly know what the system might do ("deep opacity"). If the agents, data subjects as well as analytics experts, operate under opacity, then these agents cannot provide justifications for judgments that are necessary to protect privacy, e.g., they cannot give "informed consent", or guarantee "anonymity". It follows from these points that agents in big data analytics and AI often cannot make the judgments needed to protect privacy. So I conclude that big data analytics makes the privacy problems worse and the remedies less effective. As a positive note, I provide a brief outlook on technical ways to handle this situation.

Effective Cyber Threat Intelligence (CTI) relies upon accurately structured and semantically enriched information extracted from cybersecurity system logs. However, current methodologies often struggle to identify and interpret malicious events reliably and transparently, particularly in cases involving unstructured or ambiguous log entries. In this work, we propose a novel methodology that combines ontology-driven structured outputs with Large Language Models (LLMs), to build an Artificial Intelligence (AI) agent that improves the accuracy and explainability of information extraction from cybersecurity logs. Central to our approach is the integration of domain ontologies and SHACL-based constraints to guide the language model's output structure and enforce semantic validity over the resulting graph. Extracted information is organized into an ontology-enriched graph database, enabling future semantic analysis and querying. The design of our methodology is motivated by the analytical requirements associated with honeypot log data, which typically comprises predominantly malicious activity. While our case study illustrates the relevance of this scenario, the experimental evaluation is conducted using publicly available datasets. Results demonstrate that our method achieves higher accuracy in information extraction compared to traditional prompt-only approaches, with a deliberate focus on extraction quality rather than processing speed.

Large Language Model (LLM)-enabled agents are rapidly emerging across a wide range of applications, but their deployment introduces vulnerabilities with security implications. While prior work has examined prompt-based attacks (e.g., prompt injection) and data-oriented threats (e.g., data exfiltration), time-of-check to time-of-use (TOCTOU) remain largely unexplored in this context. TOCTOU arises when an agent validates external state (e.g., a file or API response) that is later modified before use, enabling practical attacks such as malicious configuration swaps or payload injection. In this work, we present the first study of TOCTOU vulnerabilities in LLM-enabled agents. We introduce TOCTOU-Bench, a benchmark with 66 realistic user tasks designed to evaluate this class of vulnerabilities. As countermeasures, we adapt detection and mitigation techniques from systems security to this setting and propose prompt rewriting, state integrity monitoring, and tool-fusing. Our study highlights challenges unique to agentic workflows, where we achieve up to 25% detection accuracy using automated detection methods, a 3% decrease in vulnerable plan generation, and a 95% reduction in the attack window. When combining all three approaches, we reduce the TOCTOU vulnerabilities from an executed trajectory from 12% to 8%. Our findings open a new research direction at the intersection of AI safety and systems security.

Security vulnerabilities present in a code that has been written in diverse programming languages are among the most critical yet complicated aspects of source code to detect. Static analysis tools based on rule-based patterns usually do not work well at detecting the context-dependent bugs and lead to high false positive rates. Recent developments in artificial intelligence, specifically the use of transformer-based models like CodeBERT and CodeLlama, provide light to this problem, as they show potential in finding such flaws better. This paper presents the implementations of these models on various datasets of code vulnerability, showing how off-the-shelf models can successfully produce predictive capacity in models through dynamic fine-tuning of the models on vulnerable and safe code fragments. The methodology comprises the gathering of the dataset, normalization of the language, fine-tuning of the model, and incorporation of ensemble learning and explainable AI. Experiments show that a well-trained CodeBERT can be as good as or even better than some existing static analyzers in terms of accuracy greater than 97%. Further study has indicated that although language models can achieve close-to-perfect recall, the precision can decrease. A solution to this is given by hybrid models and validation procedures, which will reduce false positives. According to the results, the AI-based solutions generalize to different programming languages and classes of vulnerability. Nevertheless, robustness, interpretability, and deployment readiness are still being developed. The results illustrate the probabilities that AI will enhance the trustworthiness in the usability and scalability of machine-learning-based detectors of vulnerabilities.