Generative models have achieved impressive results in text to image tasks, significantly advancing visual content creation. However, this progress comes at a cost, as such models rely heavily on large-scale training data and may unintentionally replicate copyrighted elements, creating serious legal and ethical challenges for real-world deployment. To address these concerns, researchers have proposed various strategies to mitigate copyright risks, most of which are prompt based methods that filter or rewrite user inputs to prevent explicit infringement. While effective in handling obvious cases, these approaches often fall short in more subtle situations, where seemingly benign prompts can still lead to infringing outputs. To address these limitations, this paper introduces Assessing and Mitigating Copyright Risks (AMCR), a comprehensive framework which i) builds upon prompt-based strategies by systematically restructuring risky prompts into safe and non-sensitive forms, ii) detects partial infringements through attention-based similarity analysis, and iii) adaptively mitigates risks during generation to reduce copyright violations without compromising image quality. Extensive experiments validate the effectiveness of AMCR in revealing and mitigating latent copyright risks, offering practical insights and benchmarks for the safer deployment of generative models.

--In federated learning, participants' uploaded model updates cannot be directly verified, leaving the system vulnerable to malicious attacks. Existing attack strategies have adversaries upload tampered model updates to degrade the global model's performance. In real-world scenarios, attackers are driven by self-centered motives: their goal is to gain a competitive advantage by developing a model that outperforms those of other participants, not merely to cause disruption. In this paper, we study a novel Self-Centered Federated Learning (SCFL) attack paradigm, in which attackers not only degrade the performance of the global model through attacks but also enhance their own models within the federated learning process. We propose a framework named FedThief, which degrades the performance of the global model by uploading modified content during the upload stage. At the same time, it enhances the private model's performance through divergence-aware ensemble techniques--where "divergence" quantifies the deviation between private and global models--that integrate global updates and local knowledge. Extensive experiments show that our method effectively degrades the global model performance while allowing the attacker to obtain an ensemble model that significantly outperforms the global model. N the field of machine learning, the quality and diversity of the training data are widely recognized as essential prerequisites for enabling models to generalize effectively to unseen data and perform reliably across a range of downstream tasks [1], [2]. These characteristics directly influence the learned model's empirical risk minimization, hypothesis space coverage, and robustness to distributional shifts [3], [4].

Air pollution monitoring in resource-constrained regions remains challenging due to sparse sensor deployment and limited infrastructure. This work introduces AQFusionNet, a multimodal deep learning framework for robust Air Quality Index (AQI) prediction. The framework integrates ground-level atmospheric imagery with pollutant concentration data using lightweight CNN backbones (MobileNetV2, ResNet18, EfficientNet-B0). Visual and sensor features are combined through semantically aligned embedding spaces, enabling accurate and efficient prediction. Experiments on more than 8,000 samples from India and Nepal demonstrate that AQFusionNet consistently outperforms unimodal baselines, achieving up to 92.02% classification accuracy and an RMSE of 7.70 with the EfficientNet-B0 backbone. The model delivers an 18.5% improvement over single-modality approaches while maintaining low computational overhead, making it suitable for deployment on edge devices. AQFusionNet provides a scalable and practical solution for AQI monitoring in infrastructure-limited environments, offering robust predictive capability even under partial sensor availability.

We introduce GIER (Gap-driven Iterative Enhancement of Responses), a general framework for improving large language model (LLM) outputs through self-reflection and revision based on conceptual quality criteria. Unlike prompting strategies that rely on demonstrations, examples, or chain-of-thought templates, GIER utilizes natural language descriptions of reasoning gaps, and prompts a model to iteratively critique and refine its own outputs to better satisfy these criteria. Across three reasoning-intensive tasks (SciFact, PrivacyQA, and e-SNLI) and four LLMs (GPT-4.1, GPT-4o Mini, Gemini 1.5 Pro, and Llama 3.3 70B), GIER improves rationale quality, grounding, and reasoning alignment without degrading task accuracy. Our analysis demonstrates that models can not only interpret abstract conceptual gaps but also translate them into concrete reasoning improvements.

As organizations face increasing pressure to understand their corporate and products' carbon footprints, artificial intelligence (AI)-assisted calculation systems for footprinting are proliferating, but with widely varying levels of rigor and transparency. Standards and guidance have not kept pace with the technology; evaluation datasets are nascent; and statistical approaches to uncertainty analysis are not yet practical to apply to scaled systems. We present a set of criteria to validate AI-assisted systems that calculate greenhouse gas (GHG) emissions for products and materials. We implement a three-step approach: (1) Identification of needs and constraints, (2) Draft criteria development and (3) Refinements through pilots. The process identifies three use cases of AI applications: Case 1 focuses on AI-assisted mapping to existing datasets for corporate GHG accounting and product hotspotting, automating repetitive manual tasks while maintaining mapping quality. Case 2 addresses AI systems that generate complete product models for corporate decision-making, which require comprehensive validation of both component tasks and end-to-end performance. We discuss the outlook for Case 3 applications, systems that generate standards-compliant models. We find that credible AI systems can be built and that they should be validated using system-level evaluations rather than line-item review, with metrics such as benchmark performance, indications of data quality and uncertainty, and transparent documentation. This approach may be used as a foundation for practitioners, auditors, and standards bodies to evaluate AI-assisted environmental assessment tools. By establishing evaluation criteria that balance scalability with credibility requirements, our approach contributes to the field's efforts to develop appropriate standards for AI-assisted carbon footprinting systems.

We study notions of (virtual) group knowledge and group belief within multi-agent evidence models, obtained by extending the topological semantics of evidence-based belief and fallible knowledge from individuals to groups. We completely axiomatize and show the decidability of the logic of ("hard" and "soft") group evidence, and do the same for an especially interesting fragment of it: the logic of group knowledge and group belief. We also extend these languages with dynamic evidence-sharing operators, and completely axiomatize the corresponding logics, showing that they are co-expressive with their static bases.

The rapid growth of statutory corpora and judicial decisions requires scalable legal AI systems capable of classification and retrieval over extremely long contexts. Transformer-based architectures (e.g., Longformer, DeBERTa) dominate current legal NLP benchmarks but struggle with quadratic attention costs, limiting efficiency and scalability. In this work, we present the first comprehensive benchmarking of Mamba, a state-space model (SSM) with linear-time selective mechanisms, against leading transformer models for statutory classification and case law retrieval. We evaluate models on open-source legal corpora including LexGLUE, EUR-Lex, and ILDC, covering statutory tagging, judicial outcome prediction, and case retrieval tasks. Metrics include accuracy, recall at k, mean reciprocal rank (MRR), and normalized discounted cumulative gain (nDCG), alongside throughput measured in tokens per second and maximum context length. Results show that Mamba's linear scaling enables processing of legal documents several times longer than transformers, while maintaining or surpassing retrieval and classification performance. This study introduces a new legal NLP benchmark suite for long-context modeling, along with open-source code and datasets to support reproducibility. Our findings highlight trade-offs between state-space models and transformers, providing guidance for deploying scalable legal AI in statutory analysis, judicial decision support, and policy research.

The growing societal reliance on artificial intelligence necessitates robust frameworks for ensuring its security, accountability, and trustworthiness. This thesis addresses the complex interplay between privacy, verifiability, and auditability in modern AI, particularly in foundation models. It argues that technical solutions that integrate these elements are critical for responsible AI innovation. Drawing from international policy contributions and technical research to identify key risks in the AI pipeline, this work introduces novel technical solutions for critical privacy and verifiability challenges. Specifically, the research introduces techniques for enabling verifiable and auditable claims about AI systems using zero-knowledge cryptography; utilizing secure multi-party computation and trusted execution environments for auditable, confidential deployment of large language models and information retrieval; and implementing enhanced delegation mechanisms, credentialing systems, and access controls to secure interactions with autonomous and multi-agent AI systems. Synthesizing these technical advancements, this dissertation presents a cohesive perspective on balancing privacy, verifiability, and auditability in foundation model-based AI systems, offering practical blueprints for system designers and informing policy discussions on AI safety and governance.

According to the United States Internal Revenue Service, "the average American spends $270 and 13 hours filing their taxes". Even beyond the U.S., tax filing requires complex reasoning, combining application of overlapping rules with numerical calculations. Because errors can incur costly penalties, any automated system must deliver high accuracy and auditability, making modern large language models (LLMs) poorly suited for this task. We propose an approach that integrates LLMs with a symbolic solver to calculate tax obligations. We evaluate variants of this system on the challenging StAtutory Reasoning Assessment (SARA) dataset, and include a novel method for estimating the cost of deploying such a system based on real-world penalties for tax errors. We further show how combining up-front translation of plain-text rules into formal logic programs, combined with intelligently retrieved exemplars for formal case representations, can dramatically improve performance on this task and reduce costs to well below real-world averages. Our results demonstrate the effectiveness of applying semantic parsing methods to statutory reasoning, and show promising economic feasibility of neuro-symbolic architectures for increasing access to reliable tax assistance. Code is available at https://github.com/wjurayj/legal

Recent advances in large language models have sparked growing interest in AI agents capable of solving complex, real-world tasks. However, most existing agent systems rely on manually crafted configurations that remain static after deployment, limiting their ability to adapt to dynamic and evolving environments. To this end, recent research has explored agent evolution techniques that aim to automatically enhance agent systems based on interaction data and environmental feedback. This emerging direction lays the foundation for self-evolving AI agents, which bridge the static capabilities of foundation models with the continuous adaptability required by lifelong agentic systems. In this survey, we provide a comprehensive review of existing techniques for self-evolving agentic systems. Specifically, we first introduce a unified conceptual framework that abstracts the feedback loop underlying the design of self-evolving agentic systems. The framework highlights four key components: System Inputs, Agent System, Environment, and Optimisers, serving as a foundation for understanding and comparing different strategies. Based on this framework, we systematically review a wide range of self-evolving techniques that target different components of the agent system. We also investigate domain-specific evolution strategies developed for specialised fields such as biomedicine, programming, and finance, where optimisation objectives are tightly coupled with domain constraints. In addition, we provide a dedicated discussion on the evaluation, safety, and ethical considerations for self-evolving agentic systems, which are critical to ensuring their effectiveness and reliability. This survey aims to provide researchers and practitioners with a systematic understanding of self-evolving AI agents, laying the foundation for the development of more adaptive, autonomous, and lifelong agentic systems.