Skip to content
GCC AI Research

Search

Results for "robustness"

UAE Cyber Security Council, Cisco and Open Innovation AI establish national AI test and validation lab - ZAWYA

The National ·

The UAE Cyber Security Council, in collaboration with Cisco and Open Innovation AI, has established a national AI test and validation lab in the UAE. This new lab aims to provide a secure environment for rigorously testing AI systems and applications. Its purpose is to ensure the reliability, robustness, and adherence to ethical standards of AI solutions developed and deployed across various sectors in the country. Why it matters: This initiative is crucial for fostering a secure and trustworthy AI ecosystem within the UAE, directly supporting the nation's strategic goals for advanced technology adoption and governance.

Evaluation of Adversarial Robustness in Arabic Language Models

arXiv ·

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.

Model-Structured Neural Networks to Control the Steering Dynamics of Autonomous Race Cars

arXiv ·

Researchers propose MS-NN-steer, a model-structured neural network for autonomous vehicle steering control that integrates nonlinear vehicle dynamics. The controller was validated using real-world data from the Abu Dhabi Autonomous Racing League (A2RL) competition. MS-NN-steer demonstrates improved accuracy, generalization, and robustness compared to general-purpose NNs and the A2RL winning team's controller. Why it matters: This research demonstrates a promising approach to developing transparent and reliable AI for safety-critical autonomous racing applications in the UAE.

ScoreAdv: Score-based Targeted Generation of Natural Adversarial Examples via Diffusion Models

arXiv ·

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.

How Good is my Video LMM? Complex Video Reasoning and Robustness Evaluation Suite for Video-LMMs

arXiv ·

Researchers from MBZUAI have introduced the Complex Video Reasoning and Robustness Evaluation Suite (CVRR-ES) for assessing Video-LLMs. The benchmark evaluates models across 11 real-world video dimensions, revealing challenges in robustness and reasoning, particularly for open-source models. A training-free Dual-Step Contextual Prompting (DSCP) technique is proposed to enhance Video-LMM performance, with the dataset and code made publicly available.

Provable Unrestricted Adversarial Training without Compromise with Generalizability

arXiv ·

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.

LLMEffiChecker: Understanding and Testing Efficiency Degradation of Large Language Models

arXiv ·

The paper introduces LLMEffiChecker, a tool to test the computational efficiency robustness of LLMs by identifying vulnerabilities that can significantly degrade performance. LLMEffiChecker uses both white-box (gradient-guided perturbation) and black-box (causal inference-based perturbation) methods to delay the generation of the end-of-sequence token. Experiments on nine public LLMs demonstrate that LLMEffiChecker can substantially increase response latency and energy consumption with minimal input perturbations.

Universal Adversarial Examples in Remote Sensing: Methodology and Benchmark

arXiv ·

This paper introduces a novel black-box adversarial attack method, Mixup-Attack, to generate universal adversarial examples for remote sensing data. The method identifies common vulnerabilities in neural networks by attacking features in the shallow layer of a surrogate model. The authors also present UAE-RS, the first dataset of black-box adversarial samples in remote sensing, to benchmark the robustness of deep learning models against adversarial attacks.