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.
Researchers from MBZUAI and other institutions have developed a new framework called STEREO to improve the safety of text-to-image diffusion models. STEREO uses a two-stage approach: STE (Search Thoroughly Enough) based on adversarial training and REO (Robustly Erase Once) for batch concept erasure. This framework aims to enhance safety without significantly impacting the model's performance on normal queries. Why it matters: The framework addresses vulnerabilities in AI image generation, reducing the creation of inappropriate images while preserving performance on harmless queries.
Hassan Sajjad from Dalhousie University presented research on exploring the latent space of AI models to assess their safety and trustworthiness. He discussed use cases where analyzing latent space helps understand the robustness-generalization tradeoff in adversarial training and evaluate language comprehension. Sajjad's work aims to build better AI models and increase trust in their capabilities by looking at model internals. Why it matters: Intrinsic evaluation of model internals will become important to improving AI safety and robustness.
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.