This paper introduces SemDiff, a novel method for generating unrestricted adversarial examples (UAEs) by exploring the semantic latent space of diffusion models. SemDiff uses multi-attribute optimization to ensure attack success while preserving the naturalness and imperceptibility of generated UAEs. Experiments on high-resolution datasets demonstrate SemDiff's superior performance compared to state-of-the-art methods in attack success rate and imperceptibility, while also evading defenses.
KAUST and Spire Global are collaborating on a nanosatellite mission, launching a 6U CubeSat to collect high-resolution data on global ecosystems. The satellite, equipped with GNSS-R and a hyperspectral instrument with AI capabilities, will operate for three years. KAUST researchers will use the data for mapping habitats, monitoring vegetation, studying coral reefs, and advancing precision agriculture. Why it matters: This mission will provide valuable data for environmental monitoring and support Saudi Arabia's Vision 2030 goals and the Saudi and Middle East Green Initiatives.
Researchers developed a data-driven toolkit for short-term traffic forecasting using high-resolution traffic data from urban road sensors. The method models forecasting as a matrix completion problem, mapping inputs to a higher-dimensional space using kernels and adaptive boosting. Validated using real-world data from Abu Dhabi, UAE, the method outperforms state-of-the-art algorithms.
The paper introduces a novel method for short-term, high-resolution traffic prediction, modeling it as a matrix completion problem solved via block-coordinate descent. An ensemble learning approach is used to capture periodic patterns and reduce training error. The method is validated using both simulated and real-world traffic data from Abu Dhabi, demonstrating superior performance compared to other algorithms.
KAUST, in partnership with Spire Global, has successfully launched a Cubesat satellite on the SpaceX Transporter-7 mission. The satellite is equipped with a hyperspectral camera and GNSS-R sensor to collect high-resolution data on Earth's ecosystems. The collected data will help Saudi Arabia observe and characterize its natural resources, especially in terrestrial, coastal, and ocean environments. Why it matters: The satellite launch demonstrates KAUST's commitment to advancing Vision 2030 goals related to environmental protection and provides a valuable resource for scientists and collaborators to address local and regional environmental questions.