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
Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretation
Hanjie Chen, Yangfeng Ji
Powerful Physical Adversarial Examples Against Practical Face Recognition Systems
Inderjeet Singh, Toshinori Araki, Kazuya Kakizaki
Input-specific Attention Subnetworks for Adversarial Detection
Emil Biju, Anirudh Sriram, Pratyush Kumar, Mitesh M Khapra
Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection
Liang Chen, Yong Zhang, Yibing Song, Lingqiao Liu, Jue Wang
An Intermediate-level Attack Framework on The Basis of Linear Regression
Yiwen Guo, Qizhang Li, Wangmeng Zuo, Hao Chen
A Prompting-based Approach for Adversarial Example Generation and Robustness Enhancement
Yuting Yang, Pei Huang, Juan Cao, Jintao Li, Yun Lin, Jin Song Dong, Feifei Ma, Jian Zhang
Leveraging Expert Guided Adversarial Augmentation For Improving Generalization in Named Entity Recognition
Aaron Reich, Jiaao Chen, Aastha Agrawal, Yanzhe Zhang, Diyi Yang
Leveraging Adversarial Examples to Quantify Membership Information Leakage
Ganesh Del Grosso, Hamid Jalalzai, Georg Pichler, Catuscia Palamidessi, Pablo Piantanida
On the Properties of Adversarially-Trained CNNs
Mattia Carletti, Matteo Terzi, Gian Antonio Susto
Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Input
Junyoung Byun, Seungju Cho, Myung-Joon Kwon, Hee-Seon Kim, Changick Kim