MBZUAI's Metaverse Lab is developing AI algorithms for photorealistic virtual humans and dynamic environments. Hao Li, Director of the lab, envisions using the metaverse for immersive learning experiences related to history and culture. He is also working on tools to prevent deepfakes and other cyberthreats. Why it matters: This research at MBZUAI aims to advance AI and immersive technologies for education and address potential risks in the metaverse.
This article discusses adversarial training (AT) as a method to improve the robustness of machine learning models against adversarial attacks. AT aims to correctly classify data and ensure no data fall near decision boundaries, simulating adversarial attacks during training. Dr. Jingfeng Zhang from RIKEN-AIP will present on improvements to AT and its application in evaluating and enhancing the reliability of ML methods. Why it matters: As ML models become more prevalent in real-world applications in the GCC region, ensuring their robustness against adversarial attacks is crucial for maintaining their reliability and security.
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.
The paper introduces ScoreAdv, a novel approach for generating natural adversarial examples (UAEs) using diffusion models. It incorporates an adversarial guidance mechanism and saliency maps to shift the sampling distribution and inject visual information. Experiments on ImageNet and CelebA datasets demonstrate state-of-the-art attack success rates, image quality, and robustness against defenses.
KAUST researchers have developed deepBlastoid, a deep learning tool for evaluating models of human embryo development, called blastoids. deepBlastoid can evaluate images of blastoids at speeds 1000 times faster than expert scientists, processing 273 images per second. Trained on over 2000 microscopic blastoid images, it assesses the impact of chemicals on blastoid development using over 10,000 images. Why it matters: This AI tool accelerates research into early pregnancy, fertility complications, and the impact of chemicals on embryo development, with implications for reproductive technologies.
MBZUAI researchers are working on digital twin technology that can replicate human beings in detail, with real-time data flow between the physical and virtual. This project aims to extend digital twins from objects to organic entities like humans, plants and animals. The technology mines data from cameras, sensors, wearables, and other sources to predict health issues before they arise. Why it matters: This research has the potential to transform healthcare by enabling the prediction and prevention of health issues.
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.