We show that variational learning can significantly improve the accuracy and calibration of Low-Rank Adaptation (LoRA) without a substantial increase in the cost. We replace AdamW by the Improved Variational Online Newton (IVON) algorithm to finetune large language models. For Llama-2 with 7 billion parameters, IVON improves the accuracy over AdamW by 2.8% and expected calibration error by 4.6%. The accuracy is also better than the other Bayesian alternatives, yet the cost is lower and the implementation is easier. Our work provides additional evidence for the effectiveness of IVON for large language models.

Wildfires pose significant threats to ecosystems, economies, and communities worldwide, necessitating advanced predictive methods for effective mitigation. This study introduces a novel and comprehensive dataset specifically designed for wildfire prediction in Morocco, addressing its unique geographical and climatic challenges. By integrating satellite observations and ground station data, we compile essential environmental indicators such as vegetation health (NDVI), population density, soil moisture levels, and meteorological data aimed at predicting next-day wildfire occurrences with high accuracy. Our methodology incorporates state-of-the-art machine learning and deep learning algorithms, demonstrating superior performance in capturing wildfire dynamics compared to traditional models. Preliminary results show that models using this dataset achieve an accuracy of up to 90%, significantly improving prediction capabilities. The public availability of this dataset fosters scientific collaboration, aiming to refine predictive models and develop innovative wildfire management strategies. Our work not only advances the technical field of dataset creation but also emphasizes the necessity for localized research in underrepresented regions, providing a scalable model for other areas facing similar environmental challenges.

Defending against today's increasingly sophisticated and large-scale cyberattacks demands accurate, real-time threat intelligence. Traditional approaches struggle to scale, integrate diverse telemetry, and adapt to a constantly evolving security landscape. We introduce Threat Intelligence Tracking via Adaptive Networks (TITAN), an industry-scale graph mining framework that generates cyber threat intelligence at unprecedented speed and scale. TITAN introduces a suite of innovations specifically designed to address the complexities of the modern security landscape, including: (1) a dynamic threat intelligence graph that maps the intricate relationships between millions of entities, incidents, and organizations; (2) real-time update mechanisms that automatically decay and prune outdated intel; (3) integration of security domain knowledge to bootstrap initial reputation scores; and (4) reputation propagation algorithms that uncover hidden threat actor infrastructure. Integrated into Microsoft Unified Security Operations Platform (USOP), which is deployed across hundreds of thousands of organizations worldwide, TITAN's threat intelligence powers key detection and disruption capabilities. With an impressive average macro-F1 score of 0.89 and a precision-recall AUC of 0.94, TITAN identifies millions of high-risk entities each week, enabling a 6x increase in non-file threat intelligence. Since its deployment, TITAN has increased the product's incident disruption rate by a remarkable 21%, while reducing the time to disrupt by a factor of 1.9x, and maintaining 99% precision, as confirmed by customer feedback and thorough manual evaluation by security experts--ultimately saving customers from costly security breaches.

Artificial intelligence (AI) and machine learning often address challenges that are relatively monolithic: determine the safest action for an autonomous car; translate a document from English to French; analyse a medical image to detect a cancer; answer a question about a difficult topic. These kinds of challenge are important and worthwhile targets for AI research. However, an alternative set of challenges exist that are collective in nature: help to minimise a pandemic's impact by coordinating mitigating interventions; help to manage an extreme weather event using real-time physical and social data streams; help to avoid a stock market crash by managing interactions between trading agents; help to guide city developers towards more sustainable coordinated city planning decisions; help people with diabetes to collaboratively manage their condition while preserving privacy.

AI has made significant strides recently, leading to various applications in both civilian and military sectors. The military sees AI as a solution for developing more effective and faster technologies. While AI offers benefits like improved operational efficiency and precision targeting, it also raises serious ethical and legal concerns, particularly regarding human rights violations. Autonomous weapons that make decisions without human input can threaten the right to life and violate international humanitarian law. To address these issues, we propose a three-stage framework (Design, In Deployment, and During/After Use) for evaluating human rights concerns in the design, deployment, and use of military AI. Each phase includes multiple components that address various concerns specific to that phase, ranging from bias and regulatory issues to violations of International Humanitarian Law. By this framework, we aim to balance the advantages of AI in military operations with the need to protect human rights.

The recent introduction of large language models (LLMs) has revolutionized the field of robotics by enabling contextual reasoning and intuitive human-robot interaction in domains as varied as manipulation, locomotion, and self-driving vehicles. When viewed as a stand-alone technology, LLMs are known to be vulnerable to jailbreaking attacks, wherein malicious prompters elicit harmful text by bypassing LLM safety guardrails. To assess the risks of deploying LLMs in robotics, in this paper, we introduce RoboPAIR, the first algorithm designed to jailbreak LLM-controlled robots. Unlike existing, textual attacks on LLM chatbots, RoboPAIR elicits harmful physical actions from LLM-controlled robots, a phenomenon we experimentally demonstrate in three scenarios: (i) a white-box setting, wherein the attacker has full access to the NVIDIA Dolphins self-driving LLM, (ii) a gray-box setting, wherein the attacker has partial access to a Clearpath Robotics Jackal UGV robot equipped with a GPT-4o planner, and (iii) a black-box setting, wherein the attacker has only query access to the GPT-3.5-integrated Unitree Robotics Go2 robot dog. In each scenario and across three new datasets of harmful robotic actions, we demonstrate that RoboPAIR, as well as several static baselines, finds jailbreaks quickly and effectively, often achieving 100% attack success rates. Our results reveal, for the first time, that the risks of jailbroken LLMs extend far beyond text generation, given the distinct possibility that jailbroken robots could cause physical damage in the real world. Indeed, our results on the Unitree Go2 represent the first successful jailbreak of a deployed commercial robotic system. Addressing this emerging vulnerability is critical for ensuring the safe deployment of LLMs in robotics. Additional media is available at: https://robopair.org

This study addresses critical challenges of cybersecurity in digital substations by proposing an innovative task-oriented dialogue (ToD) system for anomaly detection (AD) in multicast messages, specifically, generic object oriented substation event (GOOSE) and sampled value (SV) datasets. Leveraging generative artificial intelligence (GenAI) technology, the proposed framework demonstrates superior error reduction, scalability, and adaptability compared with traditional human-in-the-loop (HITL) processes. Notably, this methodology offers significant advantages over machine learning (ML) techniques in terms of efficiency and implementation speed when confronting novel and/or unknown cyber threats, while also maintaining model complexity and precision. The research employs advanced performance metrics to conduct a comparative assessment between the proposed AD and HITL-based AD frameworks, utilizing a hardware-in-the-loop (HIL) testbed for generating and extracting features of IEC61850 communication messages. This approach presents a promising solution for enhancing the reliability of power system operations in the face of evolving cybersecurity challenges.

According to The Exchange Act, 1934 unlawful insider trading is the abuse of access to privileged corporate information. While a blurred line between "routine" the "opportunistic" insider trading exists, detection of strategies that insiders mold to maneuver fair market prices to their advantage is an uphill battle for hand-engineered approaches. In the context of detailed high-dimensional financial and trade data that are structurally built by multiple covariates, in this study, we explore, implement and provide detailed comparison to the existing study (Deng et al. (2019)) and independently implement automated end-to-end state-of-art methods by integrating principal component analysis to the random forest (PCA-RF) followed by a standalone random forest (RF) with 320 and 3984 randomly selected, semi-manually labeled and normalized transactions from multiple industry. The settings successfully uncover latent structures and detect unlawful insider trading. Among the multiple scenarios, our best-performing model accurately classified 96.43 percent of transactions. Among all transactions the models find 95.47 lawful as lawful and $98.00$ unlawful as unlawful percent. Besides, the model makes very few mistakes in classifying lawful as unlawful by missing only 2.00 percent. In addition to the classification task, model generated Gini Impurity based features ranking, our analysis show ownership and governance related features based on permutation values play important roles. In summary, a simple yet powerful automated end-to-end method relieves labor-intensive activities to redirect resources to enhance rule-making and tracking the uncaptured unlawful insider trading transactions. We emphasize that developed financial and trading features are capable of uncovering fraudulent behaviors.

In this paper, we present a novel RRT*-based strategy for generating kinodynamically feasible paths that satisfy temporal logic specifications. Our approach integrates a robustness metric for Linear Temporal Logics (LTL) with the system's motion constraints, ensuring that the resulting trajectories are both optimal and executable. We introduce a cost function that recursively computes the robustness of temporal logic specifications while penalizing time and control effort, striking a balance between path feasibility and logical correctness. We validate our approach with simulations and real-world experiments in complex environments, demonstrating its effectiveness in producing robust and practical motion plans. This work represents a significant step towards expanding the applicability of motion planning algorithms to more complex, real-world scenarios.

Tesla's market value breached the 1tn mark in a sharp rally on Friday, on growing bets of a favorable treatment for CEO Elon Musk's companies in return for his support for President-elect Donald Trump in his poll campaign. The electric automaker's shares rose more than 6% to a more than two-year high of 315.56, after having gained 19.3% up to Thursday's close. The company crossed the 1tn valuation for the first time in more than two years. The billionaire could push for favorable regulation of autonomous vehicles that Tesla plans and also get the US National Highway Traffic Safety Administration to hold off on potential enforcement actions involving the safety of Tesla's current driver-assistance systems, a source had told Reuters. Musk has focused on self-driving vehicle technology, ditching plans to build an economy car priced at under 30,000.