An MBZUAI team developed a self-ensembling vision transformer to enhance the security of AI in medical imaging. The model aims to protect patient anonymity and ensure the validity of medical image analysis. It addresses vulnerabilities where AI systems can be manipulated, leading to misinterpretations with potentially harmful consequences in healthcare. Why it matters: This research is crucial for building trust and enabling the safe deployment of AI in sensitive medical applications, protecting against fraud and ensuring patient safety.
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.
A study compared the vulnerability of C programs generated by nine state-of-the-art Large Language Models (LLMs) using a zero-shot prompt. The researchers introduced FormAI-v2, a dataset of 331,000 C programs generated by these LLMs, and found that at least 62.07% of the generated programs contained vulnerabilities, detected via formal verification. The research highlights the need for risk assessment and validation when deploying LLM-generated code in production environments.
Adel Bibi, a KAUST alumnus and researcher at the University of Oxford, presented his research on AI safety, covering robustness, alignment, and fairness of LLMs. The research addresses challenges in AI systems, alignment issues, and fairness across languages in common tokenizers. Bibi's work includes instruction prefix tuning and its theoretical limitations towards alignment. Why it matters: This research from a leading researcher highlights the importance of addressing safety concerns in LLMs, particularly regarding alignment and fairness in the Arabic language.
This paper introduces a framework that combines machine learning for multi-class attack detection in IoT/IIoT networks with large language models (LLMs) for attack behavior analysis and mitigation suggestion. The framework uses role-play prompt engineering with RAG to guide LLMs like ChatGPT-o3 and DeepSeek-R1, and introduces new evaluation metrics for quantitative assessment. Experiments using Edge-IIoTset and CICIoT2023 datasets showed Random Forest as the best detection model and ChatGPT-o3 outperforming DeepSeek-R1 in attack analysis and mitigation.
Researchers including Dr. Najwa Aaraj developed ML-FEED, a new exploit detection framework using pattern-based techniques. The model is 70x faster than LSTMs and 75,000x faster than Transformers in exploit detection tasks, while also being slightly more accurate. The "ML-FEED" paper won best paper at the 2022 IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications. Why it matters: This research enables more efficient real-time security applications and highlights growing AI expertise in the Arab world.