This thesis explores advanced approaches to improve explainability in computer vision by analyzing and modeling the features exploited by deep neural networks. Initially, it evaluates attribution methods, notably saliency maps, by introducing a metric based on algorithmic stability and an approach utilizing Sobol indices, which, through quasi-Monte Carlo sequences, allows a significant reduction in computation time. In addition, the EVA method offers a first formulation of attribution with formal guarantees via verified perturbation analysis. Experimental results indicate that in complex scenarios these methods do not provide sufficient understanding, particularly because they identify only "where" the model focuses without clarifying "what" it perceives. Two hypotheses are therefore examined: aligning models with human reasoning -- through the introduction of a training routine that integrates the imitation of human explanations and optimization within the space of 1-Lipschitz functions -- and adopting a conceptual explainability approach. The CRAFT method is proposed to automate the extraction of the concepts used by the model and to assess their importance, complemented by MACO, which enables their visualization. These works converge towards a unified framework, illustrated by an interactive demonstration applied to the 1000 ImageNet classes in a ResNet model.

A man from Massachusetts has agreed to plead guilty to a seven-year cyberstalking campaign that included using artificial intelligence (AI) chatbots to impersonate a university professor and invite men online to her home address for sex. James Florence, 36, used platforms such as CrushOn.ai and JanitorAI, which allow users to design their own chatbots and direct them how to respond to other users during chats, including in sexually suggestive and explicit ways, according to court documents seen by the Guardian. The victim's identity has been kept confidential by law enforcement officials. Florence admitted to using the victim's personal and professional information – including her home address, date of birth and family information to instruct the chatbots to impersonate her and engage in sexual dialogue with users, per court filings. He told the chatbots to answer "yes" in the guise of his victim when a user asked whether she was sexually adventurous and fed the AI responses of what underwear she liked to wear.

From Snowpiercer to The Day After Tomorrow, countless movies and series have put forward their vision of how climate change might reshape the world. Worryingly, scientists predict that the reality might be far more shocking than anything imagined by a Hollywood studio. Now, artificial intelligence (AI) reveals what this might look like. With Google's ImageFX AI image generator, MailOnline has used the latest scientific research to predict how the world will be in 2100. As greenhouse gas levels continue to increase, scientists predict that entire cities will be plunged under water.

Query-focused summarization (QFS) gives a summary of documents to answer a query. Past QFS work assumes queries have one answer, ignoring debatable ones (Is law school worth it?). We introduce Debatable QFS (DQFS), a task to create summaries that answer debatable queries via documents with opposing perspectives; summaries must comprehensively cover all sources and balance perspectives, favoring no side. These goals elude LLM QFS systems, which: 1) lack structured content plans, failing to guide LLMs to write balanced summaries, and 2) use the same query to retrieve contexts across documents, failing to cover all perspectives specific to each document's content. To overcome this, we design MODS, a multi-LLM framework mirroring human panel discussions. MODS treats documents as individual Speaker LLMs and has a Moderator LLM that picks speakers to respond to tailored queries for planned topics. Speakers use tailored queries to retrieve relevant contexts from their documents and supply perspectives, which are tracked in a rich outline, yielding a content plan to guide the final summary. Experiments on ConflictingQA with controversial web queries and DebateQFS, our new dataset of debate queries from Debatepedia, show MODS beats SOTA by 38-59% in topic paragraph coverage and balance, based on new citation metrics. Users also find MODS's summaries to be readable and more balanced.

Information removal or suppression in large language models (LLMs) is a desired functionality, useful in AI regulation, legal compliance, safety, and privacy. LLM unlearning methods aim to remove information on demand from LLMs. Current LLM unlearning methods struggle to balance the unlearning efficacy and utility due to the competing nature of these objectives. Keeping the unlearning process computationally feasible without assuming access to the model weights is an overlooked area. We present the first agentic LLM unlearning (ALU) method, a multi-agent, retrain-free, model-agnostic approach to LLM unlearning that achieves effective unlearning while preserving the utility. Our ALU framework unlearns by involving multiple LLM agents, each designed for a specific step in the unlearning process, without the need to update model weights for any of the agents in the framework. Users can easily request any set of unlearning instances in any sequence, and ALU seamlessly adapts in real time. This is facilitated without requiring any changes in the underlying LLM model. Through extensive experiments on established benchmarks (TOFU, WMDP, WPU) and jailbreaking techniques (many shot, target masking, other languages), we demonstrate that ALU consistently stands out as the most robust LLM unlearning framework among current state-of-the-art methods while incurring a low constant-time cost. We further highlight ALU's superior performance compared to existing methods when evaluated at scale. Specifically, ALU is assessed on up to 1000 unlearning targets, exceeding the evaluation scope of all previously proposed LLM unlearning methods.

This study presents an approach that uses session and page view data collected through the CAWAL framework, enriched through specialized processes, for advanced predictive modeling and anomaly detection in web usage mining (WUM) applications. Traditional WUM methods often rely on web server logs, which limit data diversity and quality. Integrating application logs with web analytics, the CAWAL framework creates comprehensive session and page view datasets, providing a more detailed view of user interactions and effectively addressing these limitations. This integration enhances data diversity and quality while eliminating the preprocessing stage required in conventional WUM, leading to greater process efficiency. The enriched datasets, created by cross-integrating session and page view data, were applied to advanced machine learning models, such as Gradient Boosting and Random Forest, which are known for their effectiveness in capturing complex patterns and modeling non-linear relationships. These models achieved over 92% accuracy in predicting user behavior and significantly improved anomaly detection capabilities. The results show that this approach offers detailed insights into user behavior and system performance metrics, making it a reliable solution for improving large-scale web portals' efficiency, reliability, and scalability.

MarketSenseAI is a novel framework for holistic stock analysis which leverages Large Language Models (LLMs) to process financial news, historical prices, company fundamentals and the macroeconomic environment to support decision making in stock analysis and selection. In this paper, we present the latest advancements on MarketSenseAI, driven by rapid technological expansion in LLMs. Through a novel architecture combining Retrieval-Augmented Generation and LLM agents, the framework processes SEC filings and earnings calls, while enriching macroeconomic analysis through systematic processing of diverse institutional reports. We demonstrate a significant improvement in fundamental analysis accuracy over the previous version. Empirical evaluation on S\&P 100 stocks over two years (2023-2024) shows MarketSenseAI achieving cumulative returns of 125.9% compared to the index return of 73.5%, while maintaining comparable risk profiles. Further validation on S\&P 500 stocks during 2024 demonstrates the framework's scalability, delivering a 33.8% higher Sortino ratio than the market. This work marks a significant advancement in applying LLM technology to financial analysis, offering insights into the robustness of LLM-driven investment strategies.

Recent incidents highlight safety risks in Large Language Models (LLMs), motivating research into alignment methods like Constitutional AI (CAI). This paper explores CAI's self-critique mechanism on small, uncensored 7-9B parameter models: DeepSeek-R1, Gemma-2, Llama 3.1, and Qwen2.5. Using HarmBench, we demonstrate that while all models showed capacity for harm reduction through self-critique, effectiveness varied significantly, with DeepSeek-R1's explicit reasoning process yielding superior results. These findings suggest that CAI-inspired prompting strategies can enhance safety in resource-constrained models, though success depends on the model's capacity for harm detection.

Generative AI enables automated, effective manipulation at scale. Despite the growing general ethical discussion around generative AI, the specific manipulation risks remain inadequately investigated. This article outlines essential inquiries encompassing conceptual, empirical, and design dimensions of manipulation, pivotal for comprehending and curbing manipulation risks. By highlighting these questions, the article underscores the necessity of an appropriate conceptualisation of manipulation to ensure the responsible development of Generative AI technologies.

A man who was piloting a drone that collided with a firefighting aircraft working on the Palisades fire has agreed to plead guilty to a misdemeanor, pay a fine and complete community service, federal prosecutors said Friday. Peter Tripp Akemann, 56, of Culver City was charged with unsafe operation of an unmanned aircraft. He could still face up to a year in federal prison, prosecutors said. The drone, which authorities say was flying in restricted airspace on Jan. 9, put a fist-sized hole in the left wing of a Super Scooper -- a massive fixed-wing plane that can drop large amounts of water onto a fire. The collision knocked the plane out of commission for about five days and destroyed the drone.