Adversarial Example
Adversarial examples are subtly altered inputs designed to fool machine learning models, primarily deep neural networks (DNNs), into making incorrect predictions. Current research focuses on improving model robustness against these attacks, exploring techniques like ensemble methods, multi-objective representation learning, and adversarial training, often applied to architectures such as ResNets and Vision Transformers. Understanding and mitigating the threat of adversarial examples is crucial for ensuring the reliability and security of AI systems across diverse applications, from image classification and natural language processing to malware detection and autonomous driving. The development of robust defenses and effective attack detection methods remains a significant area of ongoing investigation.
Papers
A Hybrid Training-time and Run-time Defense Against Adversarial Attacks in Modulation Classification
Lu Zhang, Sangarapillai Lambotharan, Gan Zheng, Guisheng Liao, Ambra Demontis, Fabio Roli
Countermeasures Against Adversarial Examples in Radio Signal Classification
Lu Zhang, Sangarapillai Lambotharan, Gan Zheng, Basil AsSadhan, Fabio Roli
Improving the Transferability of Adversarial Examples by Feature Augmentation
Donghua Wang, Wen Yao, Tingsong Jiang, Xiaohu Zheng, Junqi Wu, Xiaoqian Chen
Enhancing robustness of data-driven SHM models: adversarial training with circle loss
Xiangli Yang, Xijie Deng, Hanwei Zhang, Yang Zou, Jianxi Yang
Exploring Layerwise Adversarial Robustness Through the Lens of t-SNE
Inês Valentim, Nuno Antunes, Nuno Lourenço
Explainable AI Security: Exploring Robustness of Graph Neural Networks to Adversarial Attacks
Tao Wu, Canyixing Cui, Xingping Xian, Shaojie Qiao, Chao Wang, Lin Yuan, Shui Yu