Research Papers

Artificial intelligence is increasingly used in medical imaging, yet its robustness to input perturbations remains a critical concern for a wide clinical adoption. To this end, we used adversarial examples to systematically probe vulnerabilities of a U-Net-based model observer for computed tomography protocol optimization, performing detection and localization of low-contrast objects in a phantom dataset. Adversarial attacks were generated using both gradient-based and optimization-based white-box methods. Fast gradient perturbations produced high misclassification rates, reaching up to 75% at intermediate perturbation levels while remaining visually imperceptible. Localization was more robust, with success rates of about 25% for small perturbations and 42% at moderate levels. In contrast, optimization-based attack achieved success rates close to 50% for both tasks. To mitigate these vulnerabilities, dynamic adversarial training was implemented. This reduced the success rate of optimization-based attacks to 7% for classification and 13% when including localization-specific training, demonstrating a substantial robustness improvement without compromising task performances, confirmed by localization receiver operating characteristic analysis. To further interpret model behavior, radiomic texture analysis was performed on original and adversarial images. While most global image statistics remain stable, specific texture-related features exhibit consistent changes in successful attacks, highlighting the model's sensitivity to subtle local intensity patterns. Overall, adversarial training improves robustness without degrading performance, while radiomic analysis reveals interpretable links between texture alterations and prediction failures, supporting more reliable and explainable AI systems for medical imaging.

Speech conveys rich emotional information. As Speech Emotion Recognition (SER) is usually deployed in privacy-sensitive and reliability-critical environments, adversarial attacks on SER have attracted increasing attention. Existing sparse attacks control the number of perturbed elements, yet, they often lack explainability guidance and explicit measures of explanation consistency. A unified treatment of sparsity and magnitude constraints is also uncommon. In addition, transferability across attack families and target models remains limited. Hence, we propose a SalIency-Guided sparse Mask Attack (SIGMA). On self-supervised speech features, we use post-hoc explainable artificial intelligence (XAI) techniques to produce saliency maps and identify the scope of the mask, and then restrict magnitude-bounded updates to this mask. The mask is computed once and can be reused across models and different sparsity attacks to amortise cost. We evaluate on the IEMOCAP and TESS datasets. Under matched budgets and across multiple sparse-attack settings, SIGMA maintains competitive attack success rates, navigating a conscious trade-off between attack efficacy and explanation consistency. SIGMA therefore provides an efficient and interpretable framework for analysing the vulnerability and explanation behaviour of SER models under structured perturbations.

With the emergence of machine learning (ML) models trained on large datasets containing potentially sensitive data, a major question in AI safety is how to make learning private with respect to the training data. Similar to classical machine learning, quantum machine learning (QML) models are not devoid of privacy vulnerabilities. Differential privacy (DP) is a standard tool for training ML models on sensitive data, but its impact in QML remains poorly understood. In this work we study private training in hybrid variational QML models using a classical private DP-SGD optimizer applied to pipelines with classical inputs and outputs. We analyze the interplay between gradient clipping and calibrated noise addition in DP-SGD, and its impact on optimization and accuracy for noisy and noiseless quantum models. We first explain why quantum noise does not provide a satisfactory replacement for the calibrated noise in DP-SGD for ensuring privacy. We then show how the deterministic bounds on gradient norms for a wide class of quantum models translate into explicit control of the detrimental clipping bias introduced by DP-SGD. Finally, we formulate a numerical comparison protocol under fixed clipping threshold and privacy budget and evaluate it on synthetic and image-classification tasks for equivalent quantum and classical models. Our results suggest that quantum models can retain higher accuracy in private-training regimes where the formal privacy guarantee is ensured by a classical DP-SGD mechanism.

As large language models are increasingly deployed in real-world systems, safety failures can still lead to harmful outputs and dangerous misuse. We argue that the essence of safety is adversarial: many failures arise not from natural inputs alone, but from strategic attempts to evade model policies and safeguards. However, existing general-purpose model development largely overlook this adversarial nature, and often remain insufficient for realistic safety scenarios involving planning, tool use, and multi-step reasoning, causing measured safety performance to overestimate real deployment robustness. To address this gap, we present Yuvion LLM, a large language model built for adversarially robust content safety and broader AI safety. Yuvion LLM treats adversarial robustness and agentic capability as first-class objectives. Its pipeline combines adversarially aware data construction, knowledge-enhanced continued pretraining, and policy-grounded multi-task safety post-training, including risk-aware supervised fine-tuning and reinforcement learning-based policy optimization, together with safety-aware agentic reinforcement learning for tool use and multi-step reasoning in complex safety scenarios. We further introduce the Yuvion LLM RiskEval (YLRE), a collection of 93 benchmarks across four evaluation categories, covering diverse open and internal evaluations with a focus on safety, adversarial robustness, and real-world capability requirements. Across these evaluations, Yuvion LLM demonstrates clear advantages on safety-focused benchmarks and particularly strong robustness under adversarial conditions, while maintaining solid overall capability. Notably, Yuvion-8B outperforms most state-of-the-art baselines, including substantially larger models such as GPT-5.4 and Qwen3-MAX, on several safety tasks.

Distributed Quality-Diversity Search for Toxicity in Large Language Models

Onkar Shelar, Travis Desell

Large Language Models remain vulnerable to adversarial prompts that elicit harmful responses, and scaling red-teaming to cover a broad range of failure modes is constrained by the cost of text generation and evaluation. We present \emph{ToxSearch-S}, a speciated extension of toxicity-focused evolutionary prompt search with incremental, embedding-driven niche maintenance, together with an MPI master-worker realization that centralizes population and species bookkeeping on rank~0 while offloading prompt evolution and evaluation to $n_w$ parallel workers. Under a common budget, ToxSearch-S attains peak toxicity competitive with both ToxSearch and RainbowPlus while following a measurably less toxic best-so-far trajectory, indicating lower cumulative search pressure. Diversity is non-uni-dimensional: RainbowPlus yields greater embedding-level spread, whereas ToxSearch-S partitions high-toxicity prompts into more localized behavioral pockets, reflected by a higher DBSCAN cluster count. MPI distribution delivers substantial wall-clock gains, approximately $1.8\times$ with two workers and $3.2\times$ with four, while leaving Best@B statistically indistinguishable from sequential execution. Four-worker runs also produce significantly larger final species cardinality and more toxicity-bearing species, without a reliable gain in global peak toxicity. These results position incremental speciation as a practical quality-diversity mechanism for AI Safety and MPI as an effective means of compressing time-to-result while preserving measured search outcomes.

Scam phone calls exploit vulnerable communities worldwide, yet research on detection has focused almost exclusively on English and other high-resource languages. In low-resource settings such as Turkish, detection is especially difficult, as annotated data is scarce and technological defenses remain limited. This research investigates how large language models (LLMs) can support scam detection in Turkish by introducing the first public multi-modal dataset of 100 aligned audio-transcript pairs of scam and benign conversations. We evaluate seven LLMs spanning three model families: Gemini 2.5 (Flash, Flash-Lite, Pro), GPT-4o, and Qwen (Max, Plus, Turbo), under three input conditions: raw audio, automatic speech-to-text transcripts, and transcripts refined by a native speaker. Our results suggest that transcript-based inputs consistently outperform direct audio processing, while human-corrected and uncorrected transcripts perform comparably. By centering a low-resource language and real world threat, this work highlights the urgent need for culturally and linguistically inclusive AI safety research and more robust multi-modal systems for fraud prevention.

A primary challenge in AI safety is the existence of adversarial examples -- slightly distorted inputs that cause a neural network (NN) to misclassify. To mitigate this problem, recent research focuses on the computation of robustness certifications, which, for a given input, determine the largest distortion the input may receive without breaking the network's prediction. Robustness certifications can be interpreted as an axis-aligned hyper-rectangle (multi-dimensional intervals). Most existing approaches focus on maximizing the certification's volume, but recent intractability results prohibit the computation of volume-optimal certifications in reasonable time. We introduce the apothem measure and show how to compute apothem-optimal certifications in a linear number of calls to a NN verifier (oracle) w.r.t. the input domain's diameter. Moreover, we prove that we cannot have a volume-optimal, oracle-based algorithm, even if we discard the oracle costs. Also, we introduce dual certifications -- an interval including all instances of a class -- thus providing apothem-minimum upper bounds to a robustness certification. Further, we present the ParallelepipedoNN system, which we evaluate on the standard MNIST and Fashion MNIST benchmarks. A preliminary comparison with existing work on the same datasets reveals at least two-fold improvement w.r.t. the minimum edge length.

Career anxiety and depression among university students present a growing challenge to mental health and academic achievement. This study proposes an Explainable AI (XAI) framework using multimodal data and Federated Learning (FL) to identify early indicators of career-related mental health problems in a privacy-preserving and culturally responsive manner. The framework combines structured behavioral data and facial emotion features from interview videos via an intermediate fusion neural network with attention mechanisms. Label smoothing was applied to improve model generalizability. FL was used across institutions to enable collaborative training without raw data sharing. Evaluation was conducted using the Student Mental Health Survey dataset from university students across Pakistan. Our model attained an F1-score of 89.12%, recall of 86.54%, accuracy of 92.08%, and precision of 91.88%. Using Integrated Gradients and SHAP, the model identified key behavioral markers of depression including avoidance of direct gaze, lower facial expressiveness, and social withdrawal, consistent with psychological theory. This research presents an interpretable, scalable, and context-sensitive AI system for mental health pre-diagnosis with potential integration into student support services globally.

Federated Learning (FL) has emerged as a key paradigm for privacy-preserving collaborative model training across distributed and heterogeneous data sources. By keeping raw data local, FL addresses data confidentiality concerns, yet it does not resolve the opacity of modern machine learning models. In parallel, Explainable Artificial Intelligence (XAI) has gained attention for improving transparency, trust, and accountability, particularly in high-stakes domains. Their intersection has given rise to Federated Explainable Artificial Intelligence (FedXAI) paradigm, which aims to jointly satisfy privacy and explainability requirements. This survey provides a systematic review of FedXAI, highlighting the transition of explainability from a post-hoc tool to an integral component of the FL lifecycle. We show how explainability supports aggregation, personalization, robustness, coordination, and system-level decision making. To organize the literature, we introduce a taxonomy that classifies FedXAI methods by the role of explainability, model and explainer types, explanation scope, integration level, FL settings, and data heterogeneity. We review approaches ranging from model-agnostic explanations to interpretable federated models and explainability-aware aggregation mechanisms. We also examine evaluation practices and discuss the lack of standardized benchmarks and metrics for measuring explanation quality, stability, privacy leakage, and computational overhead. Finally, we identify key challenges, including explainability under non-IID data, explanation-centric security threats, communication-efficient XAI, continual FedXAI, and the integration of domain knowledge and regulatory constraints. By consolidating existing work and identifying key gaps, this survey serves as a reference framework for designing trustworthy, transparent, and privacy-preserving federated AI systems.

This paper investigates the fragility of post-hoc explanation methods in audio deepfake detection. While previous work on explanation manipulation focused on images using standard $L_p$ metrics, we introduce a psychoacoustic framework that optimizes inaudible perturbations to decouple model attributions from final classifications. We evaluate this vulnerability across state-of-the-art architectures under strict prediction-preserving constraints. By evaluating the manipulation cost through domain-specific perceptual audio quality metrics alongside explanation alignment criteria, our framework demonstrates that an adversary can systematically distort automated explanation heatmaps while preserving the predicted deepfake label. Full code available at: https://github.com/cncPomper/Audio-XAI

The UK government has adopted a pro-AI stance to help transform public service delivery in the face of severe financial pressures, but the path to translate this vision into responsible AI practice remains ill-defined. While UK policy is often set at the national level, local authorities are responsible for most public service delivery, and the rapid advance of AI-first narratives in the public sector is exposing fault lines in knowledge and practice at this national-local interface. This paper examines how responsible AI is interpreted and implemented at the interface between the UK's central government and local authorities, taking the high-stakes area of Special Educational Needs and Disabilities (SEND) as a case study. We present a thematic analysis of 17 semi-structured interviews with policymakers, practitioners, and third-sector professionals to identify barriers and enabling conditions for responsible AI where national policy meets local practice. We identify five interconnected challenges facing local authorities: shadow usage of AI and data privacy risks, market-government asymmetry in AI provision, insufficient workforce readiness, a lack of standardised definitions and measurements, and gaps in human accountability. For each, participants proposed actionable steps, from strengthening data protection frameworks and rebalancing the market-government relationship to enhancing workforce capacity. Our examination of SEND brings these challenges into sharper focus, showing how high-stakes decisions affecting vulnerable children and families intensify tensions around accountability, fairness, and human oversight, exposing the limits of a principle-based regulatory approach. We argue that responsible public sector AI requires both national policy adjustments and structural reforms to institutional capacity, values, and governance mechanisms at the local level.

The advancement of AI capabilities compels researchers and the public to be more aware of its potential worldwide impact. A pressing near-term concern is the regulation of military AI applications. Armament manufacturers and defense contractors are increasingly investing in AI capabilities and forging partnerships with AI companies, creating a burgeoning coalition that demands military leaders, arms control diplomacy experts, and AI researchers collaborate to ensure a safer future. While AI researchers often focus on the long-term implications of superintelligent AI, this approach may not adequately address the immediate challenges posed by AI in military applications. Success requires acknowledging and mitigating the emerging risks of frontier AI models that plan to be integrated into defense applications, like military AI systems. Arms control has reduced past catastrophic risks, so lessons learned from nuclear deterrence can guide AI safety and security research towards innovations in verification and diplomacy. AI researchers, however, must assist in leading the technical research that clearly defines and alleviates instability in military settings. Given these new responsibilities and the lack of sufficiently reliable solutions, we argue that AI researchers must take a leading role in advancing arms control research to minimize risk in military AI applications.