This study evaluated the adversarial robustness of five state-of-the-art Arabic Language Models against various Arabic adversarial attacks at character, word, and sentence levels. It found that diacritic insertion could reduce model accuracy by up to 92%, while manipulating Arabic conjunctions led to a 58% accuracy degradation, and paraphrasing reduced performance by an average of 76%. While adversarial training improved overall resilience, particularly for MARBERT and AraBERT, challenges against character-level noise persist. Why it matters: These findings are crucial for understanding and mitigating security vulnerabilities in Arabic AI, guiding the development of more robust and safe Arabic NLP systems.
This paper introduces Provable Unrestricted Adversarial Training (PUAT), a novel adversarial training approach. PUAT enhances robustness against both unrestricted and restricted adversarial examples while improving standard generalizability by aligning the distributions of adversarial examples, natural data, and the classifier's learned distribution. The approach uses partially labeled data and an augmented triple-GAN to generate effective unrestricted adversarial examples, demonstrating superior performance on benchmarks.
MBZUAI Professor Salman Khan is researching continuous, lifelong learning systems for computer vision, aiming to mimic human learning processes like curiosity and discovery. His work focuses on learning from limited data and adversarial robustness of deep neural networks. Khan, along with MBZUAI professors Fahad Khan and Rao Anwer, and partners from other universities, presented research at CVPR 2022. Why it matters: This research has the potential to significantly improve the ability of AI systems to understand and adapt to the real world, enabling more intelligent autonomous systems.