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
On Adversarial Examples for Text Classification by Perturbing Latent Representations
Korn Sooksatra, Bikram Khanal, Pablo Rivas
Is ReLU Adversarially Robust?
Korn Sooksatra, Greg Hamerly, Pablo Rivas
Cutting through buggy adversarial example defenses: fixing 1 line of code breaks Sabre
Nicholas Carlini
Competitive strategies to use "warm start" algorithms with predictions
Vaidehi Srinivas, Avrim Blum
Exploring Frequencies via Feature Mixing and Meta-Learning for Improving Adversarial Transferability
Juanjuan Weng, Zhiming Luo, Shaozi Li
How Real Is Real? A Human Evaluation Framework for Unrestricted Adversarial Examples
Dren Fazlija, Arkadij Orlov, Johanna Schrader, Monty-Maximilian Zühlke, Michael Rohs, Daniel Kudenko
AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation
Heqi Peng, Yunhong Wang, Ruijie Yang, Beichen Li, Rui Wang, Yuanfang Guo