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
Exploiting the Potential of Datasets: A Data-Centric Approach for Model Robustness
Yiqi Zhong, Lei Wu, Xianming Liu, Junjun Jiang
Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack
Ye Liu, Yaya Cheng, Lianli Gao, Xianglong Liu, Qilong Zhang, Jingkuan Song
Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity
Cheng Luo, Qinliang Lin, Weicheng Xie, Bizhu Wu, Jinheng Xie, Linlin Shen
Improving Neural ODEs via Knowledge Distillation
Haoyu Chu, Shikui Wei, Qiming Lu, Yao Zhao
Adaptative Perturbation Patterns: Realistic Adversarial Learning for Robust Intrusion Detection
João Vitorino, Nuno Oliveira, Isabel Praça
Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon
Yiqi Zhong, Xianming Liu, Deming Zhai, Junjun Jiang, Xiangyang Ji
Improving Health Mentioning Classification of Tweets using Contrastive Adversarial Training
Pervaiz Iqbal Khan, Shoaib Ahmed Siddiqui, Imran Razzak, Andreas Dengel, Sheraz Ahmed
Detection of Word Adversarial Examples in Text Classification: Benchmark and Baseline via Robust Density Estimation
KiYoon Yoo, Jangho Kim, Jiho Jang, Nojun Kwak