MBZUAI researchers presented a NeurIPS 2024 Spotlight paper that quantifies AI vulnerability by measuring bits leaked per query. Their formula predicts the minimum queries needed for attacks based on mutual information between model output and attacker's target. Experiments across seven models and three attack types (system-prompt extraction, jailbreaks, relearning) validate the relationship. Why it matters: This work offers a framework to translate UI choices (like exposing log-probs or chain-of-thought) into concrete attack surfaces, informing more secure AI design and deployment in the region.
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.
The United Arab Emirates is reportedly experiencing a high volume of cyberattacks, reaching up to 700,000 incidents daily, as reported by Gulf News. These attacks are occurring amid heightened regional tensions, indicating a sophisticated and persistent threat landscape. This ongoing situation poses significant challenges to the UAE's digital infrastructure and national security. Why it matters: This high frequency of cyberattacks underscores the critical need for advanced cybersecurity measures and the potential for AI-driven defense solutions in the region to protect vital infrastructure and data amidst geopolitical instability.