Research Papers

Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. However, their potential to generate harmful responses has raised significant societal and regulatory concerns, especially when manipulated by adversarial techniques known as "jailbreak" attacks. Existing jailbreak methods typically involve appending carefully crafted prefixes or suffixes to malicious prompts in order to bypass the built-in safety mechanisms of these models. In this work, we identify a new vulnerability in which excessive linguistic complexity can disrupt built-in safety mechanisms-without the need for any added prefixes or suffixes-allowing attackers to elicit harmful outputs directly. We refer to this phenomenon as Information Overload. To automatically exploit this vulnerability, we propose InfoFlood, a jailbreak attack that transforms malicious queries into complex, information-overloaded queries capable of bypassing built-in safety mechanisms. Specifically, InfoFlood: (1) uses linguistic transformations to rephrase malicious queries, (2) identifies the root cause of failure when an attempt is unsuccessful, and (3) refines the prompt's linguistic structure to address the failure while preserving its malicious intent. We empirically validate the effectiveness of InfoFlood on four widely used LLMs-GPT-4o, GPT-3.5-turbo, Gemini 2.0, and LLaMA 3.1-by measuring their jailbreak success rates. InfoFlood consistently outperforms baseline attacks, achieving up to 3 times higher success rates across multiple jailbreak benchmarks. Furthermore, we demonstrate that commonly adopted post-processing defenses, including OpenAI's Moderation API, Perspective API, and SmoothLLM, fail to mitigate these attacks. This highlights a critical weakness in traditional AI safety guardrails when confronted with information overload-based jailbreaks.

Large Language Models (LLMs) and generative AI (GenAI) systems, such as ChatGPT, Claude, Gemini, LLaMA, and Copilot (by OpenAI, Anthropic, Google, Meta, and Microsoft, respectively), are reshaping digital platforms and app ecosystems while introducing critical challenges in cybersecurity, privacy, and platform integrity. Our analysis reveals alarming trends: LLM-assisted malware is projected to rise from 2% (2021) to 50% (2025); AI-generated Google reviews grew nearly tenfold (1.2% in 2021 to 12.21% in 2023, expected to reach 30% by 2025); AI scam reports surged 456%; misinformation sites increased over 1500%; and deepfake attacks are projected to rise over 900% in 2025. In finance, LLM-driven threats like synthetic identity fraud and AI-generated scams are accelerating. Platforms such as JPMorgan Chase, Stripe, and Plaid deploy LLMs for fraud detection, regulation parsing, and KYC/AML automation, reducing fraud loss by up to 21% and accelerating onboarding by 40-60%. LLM-facilitated code development has driven mobile app submissions from 1.8 million (2020) to 3.0 million (2024), projected to reach 3.6 million (2025). To address AI threats, platforms like Google Play, Apple App Store, GitHub Copilot, TikTok, Facebook, and Amazon deploy LLM-based defenses, highlighting their dual nature as both threat sources and mitigation tools. In clinical diagnostics, LLMs raise concerns about accuracy, bias, and safety, necessitating strong governance. Drawing on 445 references, this paper surveys LLM/GenAI and proposes a strategic roadmap and operational blueprint integrating policy auditing (such as CCPA and GDPR compliance), fraud detection, and demonstrates an advanced LLM-DA stack with modular components, multi-LLM routing, agentic memory, and governance layers. We provide actionable insights, best practices, and real-world case studies for scalable trust and responsible innovation.

The recent success of generative AI highlights the crucial role of high-quality human feedback in building trustworthy AI systems. However, the increasing use of large language models (LLMs) by crowdsourcing workers poses a significant challenge: datasets intended to reflect human input may be compromised by LLM-generated responses. Existing LLM detection approaches often rely on high-dimensional training data such as text, making them unsuitable for annotation tasks like multiple-choice labeling. In this work, we investigate the potential of peer prediction -- a mechanism that evaluates the information within workers' responses without using ground truth -- to mitigate LLM-assisted cheating in crowdsourcing with a focus on annotation tasks. Our approach quantifies the correlations between worker answers while conditioning on (a subset of) LLM-generated labels available to the requester. Building on prior research, we propose a training-free scoring mechanism with theoretical guarantees under a crowdsourcing model that accounts for LLM collusion. We establish conditions under which our method is effective and empirically demonstrate its robustness in detecting low-effort cheating on real-world crowdsourcing datasets.

A common practice of ML systems development concerns the training of the same model under different data sets, and the use of the same (training and test) sets for different learning models. The first case is a desirable practice for identifying high quality and unbiased training conditions. The latter case coincides with the search for optimal models under a common dataset for training. These differently obtained systems have been considered akin to copies. In the quest for responsible AI, a legitimate but hardly investigated question is how to verify that trustworthiness is preserved by copies. In this paper we introduce a calculus to model and verify probabilistic complex queries over data and define four distinct notions: Justifiably, Equally, Weakly and Almost Trustworthy which can be checked analysing the (partial) behaviour of the copy with respect to its original. We provide a study of the relations between these notions of trustworthiness, and how they compose with each other and under logical operations. The aim is to offer a computational tool to check the trustworthiness of possibly complex systems copied from an original whose behavour is known.

Automatic reading aloud evaluation can provide valuable support to teachers by enabling more efficient scoring of reading exercises. However, research on reading evaluation systems and applications remains limited. We present a novel multimodal approach that leverages audio and knowledge from text resources. In particular, we explored the potential of using Whisper and instruction-tuned large language models (LLMs) with prompts to improve transcriptions for child speech recognition, as well as their effectiveness in downstream reading mistake detection. Our results demonstrate the effectiveness of prompting Whisper and prompting LLM, compared to the baseline Whisper model without prompting. The best performing system achieved state-of-the-art recognition performance in Dutch child read speech, with a word error rate (WER) of 5.1%, improving the baseline WER of 9.4%. Furthermore, it significantly improved reading mistake detection, increasing the F1 score from 0.39 to 0.73.

XAI-Units: Benchmarking Explainability Methods with Unit Tests

Jun Rui Lee, Sadegh Emami, Michael David Hollins +5

Feature attribution (FA) methods are widely used in explainable AI (XAI) to help users understand how the inputs of a machine learning model contribute to its outputs. However, different FA models often provide disagreeing importance scores for the same model. In the absence of ground truth or in-depth knowledge about the inner workings of the model, it is often difficult to meaningfully determine which of the different FA methods produce more suitable explanations in different contexts. As a step towards addressing this issue, we introduce the open-source XAI-Units benchmark, specifically designed to evaluate FA methods against diverse types of model behaviours, such as feature interactions, cancellations, and discontinuous outputs. Our benchmark provides a set of paired datasets and models with known internal mechanisms, establishing clear expectations for desirable attribution scores. Accompanied by a suite of built-in evaluation metrics, XAI-Units streamlines systematic experimentation and reveals how FA methods perform against distinct, atomic kinds of model reasoning, similar to unit tests in software engineering. Crucially, by using procedurally generated models tied to synthetic datasets, we pave the way towards an objective and reliable comparison of FA methods.

Counterfactual explanations play a pivotal role in explainable artificial intelligence (XAI) by offering intuitive, human-understandable alternatives that elucidate machine learning model decisions. Despite their significance, existing methods for generating counterfactuals often require constant access to the predictive model, involve computationally intensive optimization for each instance and lack the flexibility to adapt to new user-defined constraints without retraining. In this paper, we propose DiCoFlex, a novel model-agnostic, conditional generative framework that produces multiple diverse counterfactuals in a single forward pass. Leveraging conditional normalizing flows trained solely on labeled data, DiCoFlex addresses key limitations by enabling real-time user-driven customization of constraints such as sparsity and actionability at inference time. Extensive experiments on standard benchmark datasets show that DiCoFlex outperforms existing methods in terms of validity, diversity, proximity, and constraint adherence, making it a practical and scalable solution for counterfactual generation in sensitive decision-making domains.

Recent efforts to develop trustworthy AI systems have increased interest in learning problems with explicit requirements, or constraints. In deep learning, however, such problems are often handled through fixed weighted-sum penalization: the constraints are added to the task loss with fixed coefficients, and the resulting scalarized objective is minimized. This position paper argues that fixed penalization is often ill-suited for deep learning problems with non-negotiable requirements for several reasons. First, in non-convex settings, the penalized and constrained problems are generally not equivalent, so solving the former need not solve the latter. Second, fixed penalization weakens hard requirements into soft penalties to be traded off against task performance. Third, choosing penalty coefficients to indirectly solve the constrained problem often involves costly trial and error, because changing them alters the penalized objective itself, and hence can mean solving the wrong problem altogether. We therefore argue that, when a deep learning problem specifies non-negotiable requirements, the constrained formulation itself should be the starting point, not the surrogate problem defined by fixed penalization. The appropriate solution strategy should then be chosen based on the problem's structure and scale.

Large Language Models (LLMs) such as GPT, LLaMA, and Claude achieve remarkable performance in text generation but remain opaque in their decision-making processes, limiting trust and accountability in high-stakes applications. We present gSMILE (generative SMILE), a model-agnostic, perturbation-based framework for token-level interpretability in LLMs. Extending the SMILE methodology, gSMILE uses controlled prompt perturbations, Wasserstein distance metrics, and weighted linear surrogates to identify input tokens with the most significant impact on the output. This process enables the generation of intuitive heatmaps that visually highlight influential tokens and reasoning paths. We evaluate gSMILE across leading LLMs (OpenAI's gpt-3.5-turbo-instruct, Meta's LLaMA 3.1 Instruct Turbo, and Anthropic's Claude 2.1) using attribution fidelity, attribution consistency, attribution stability, attribution faithfulness, and attribution accuracy as metrics. Results show that gSMILE delivers reliable human-aligned attributions, with Claude 2.1 excelling in attention fidelity and GPT-3.5 achieving the highest output consistency. These findings demonstrate gSMILE's ability to balance model performance and interpretability, enabling more transparent and trustworthy AI systems.

Artificial Intelligence (AI) is one of the major technological advancements of this century, bearing incredible potential for users through AI-powered applications and tools in numerous domains. Being often black-box (i.e., its decision-making process is unintelligible), developers typically resort to eXplainable Artificial Intelligence (XAI) techniques to interpret the behaviour of AI models to produce systems that are transparent, fair, reliable, and trustworthy. However, presenting explanations to the user is not trivial and is often left as a secondary aspect of the system's design process, leading to AI systems that are not useful to end-users. This paper presents a Systematic Literature Review on Explanation User Interfaces (XUIs) to gain a deeper understanding of the solutions and design guidelines employed in the academic literature to effectively present explanations to users. To improve the contribution and real-world impact of this survey, we also present a platform to support Human-cEnteRed developMent of Explainable user interfaceS (HERMES) and guide practitioners and scholars in the design and evaluation of XUIs.

Composites are amongst the most important materials manufactured today, as evidenced by their use in countless applications. In order to establish the suitability of composites in specific applications, finite element (FE) modelling, a numerical method based on partial differential equations, is the industry standard for assessing their mechanical properties. However, FE modelling is exceptionally costly from a computational viewpoint, a limitation which has led to efforts towards applying AI models to this task. However, in these approaches: the chosen model architectures were rudimentary, feed-forward neural networks giving limited accuracy; the studies focused on predicting elastic mechanical properties, without considering material strength limits; and the models lacked transparency, hindering trustworthiness by users. In this paper, we show that convolutional neural networks (CNNs) equipped with methods from explainable AI (XAI) can be successfully deployed to solve this problem. Our approach uses customised CNNs trained on a dataset we generate using transverse tension tests in FE modelling to predict composites' mechanical properties, i.e., Young's modulus and yield strength. We show empirically that our approach achieves high accuracy, outperforming a baseline, ResNet-34, in estimating the mechanical properties. We then use SHAP and Integrated Gradients, two post-hoc XAI methods, to explain the predictions, showing that the CNNs use the critical geometrical features that influence the composites' behaviour, thus allowing engineers to verify that the models are trustworthy by representing the science of composites.

As artificial intelligence (AI) regulations evolve and the regulatory landscape develops and becomes more complex, ensuring compliance with ethical guidelines and legal frameworks remains a challenge for AI developers. This paper introduces an AI-driven self-assessment chatbot designed to assist users in navigating the European Union AI Act and related standards. Leveraging a Retrieval-Augmented Generation (RAG) framework, the chatbot enables real-time, context-aware compliance verification by retrieving relevant regulatory texts and providing tailored guidance. By integrating both public and proprietary standards, it streamlines regulatory adherence, reduces complexity, and fosters responsible AI development. The paper explores the chatbot's architecture, comparing naive and graph-based RAG models, and discusses its potential impact on AI governance.