Researchers have developed a scalable pre-screening framework that integrates climate and remote sensing data to identify cost-efficient sites for sustainable dryland restoration, using Saudi Arabia as a case study. The framework employs machine learning models to derive a Climate Suitability Score (CSS), which captures climatic dependencies on vegetation persistence. National-scale prediction maps were generated using multi-year ERA5-Land data for Saudi Arabia, leading to the identification of thirteen priority locations with an estimated potential for a 2.5-fold increase in vegetation coverage. Why it matters: This approach significantly reduces the search space and costs associated with restoration efforts, supporting more resilient and sustainable ecosystem recovery planning in water-limited regions of the Middle East.
Technology Innovation Institute (TII) and Mila, the Quebec AI Institute, announced a strategic partnership to collaborate on AI safety and next-generation machine learning models. TII will establish a research lab at Mila in Montreal, enabling collaboration between UAE-based researchers and Mila's AI specialists. The partnership aims to translate scientific advances into real-world impact and strengthen the global research ecosystem. Why it matters: This collaboration enhances UAE-Canada scientific ties, positioning both communities for breakthroughs in areas like LLMs and AI safety, aligning with the UAE's vision to become a global AI research hub.
The paper introduces VENOM, a text-driven framework for generating high-quality unrestricted adversarial examples using diffusion models. VENOM unifies image content generation and adversarial synthesis into a single reverse diffusion process, enhancing both attack success rate and image quality. The framework incorporates an adaptive adversarial guidance strategy with momentum to ensure the generated adversarial examples align with the distribution of natural images.
KAUST Ph.D. student Mohammed Aljahdali received the Best Paper award at the International Conference on Federated Learning Technologies and Applications (FLTA) 2025 for his research on federated learning. His paper, "Flashback: Understanding and Mitigating Forgetting in Federated Learning," introduces an algorithm to help AI systems retain knowledge across diverse datasets while preserving privacy. Aljahdali's research, supervised by Professor Marco Canini, focuses on training machine learning models directly on user devices. Why it matters: This award recognizes the growing talent and impactful research emerging from Saudi universities in the field of privacy-preserving AI.
Researchers introduce TII-SSRC-23, a new network intrusion detection dataset designed to improve the diversity and representation of modern network traffic for machine learning models. The dataset includes a range of traffic types and subtypes to address the limitations of existing datasets. Feature importance analysis and baseline experiments for supervised and unsupervised intrusion detection are also provided.
Researchers studied user lifetime prediction in the location-based social network Jodel within Saudi Arabia, leveraging its disjoint communities. Machine learning models, particularly Random Forest, were trained to predict user lifetime as a regression and classification problem. A single countrywide model generalizes well and performs similarly to community-specific models.
KAUST Professor Peter Richtárik received a Distinguished Speaker Award at the Sixth International Conference on Continuous Optimization (ICCOPT 2019) in Berlin. Richtárik's lecture series, totaling six hours, focused on stochastic gradient descent (SGD) methods, drawing from recent research by his KAUST group. He highlighted key principles and new variants of SGD, the key method for training modern machine learning models. Why it matters: This award recognizes KAUST's contribution to fundamental machine learning optimization, which is critical for advancing AI in the region.
MBZUAI is developing AI technologies to improve understanding and conservation of marine environments. AI algorithms analyze data from satellite imagery, ROVs, and sensors to identify patterns and trends, with machine learning models predicting oceanographic phenomena. Computer vision automates the identification of marine organisms, aiding in biodiversity assessments and ecosystem health evaluations. Why it matters: This research supports sustainability goals, such as improving biodiversity assessments and enabling faster responses to environmental events in the region's sensitive marine ecosystems.