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
Focused Adversarial Attacks
Thomas Cilloni, Charles Walter, Charles Fleming
Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantification
Leo Schwinn, Leon Bungert, An Nguyen, René Raab, Falk Pulsmeyer, Doina Precup, Björn Eskofier, Dario Zanca
On Trace of PGD-Like Adversarial Attacks
Mo Zhou, Vishal M. Patel
On Fragile Features and Batch Normalization in Adversarial Training
Nils Philipp Walter, David Stutz, Bernt Schiele
Boosting Adversarial Transferability of MLP-Mixer
Haoran Lyu, Yajie Wang, Yu-an Tan, Huipeng Zhou, Yuhang Zhao, Quanxin Zhang
Self-recoverable Adversarial Examples: A New Effective Protection Mechanism in Social Networks
Jiawei Zhang, Jinwei Wang, Hao Wang, Xiangyang Luo