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

September 21, 2023

September 20, 2023

PRAT: PRofiling Adversarial aTtacks
Rahul Ambati, Naveed Akhtar, Ajmal Mian, Yogesh Singh Rawat
Adversarial Attack Adversarial Example Adversarial Sample Adversarial Datasets

September 19, 2023

September 18, 2023

Reducing Adversarial Training Cost with Gradient Approximation
Huihui Gong
Adversarial Example Adversarial Training Adversarial Loss Gradient Approximation Projected Gradient Descent Efficient Adversarial Training

September 16, 2023

Context-aware Adversarial Attack on Named Entity Recognition
Shuguang Chen, Leonardo Neves, Thamar Solorio
Adversarial Example Entity Recognition Large Pre Trained Language Model

September 15, 2023

Adversarial Attacks on Tables with Entity Swap
Aneta Koleva, Martin Ringsquandl, Volker Tresp
Adversarial Attack Adversarial Example Named Entity Recognition Table Semantics Table Representation Orphan Entity Allocation Tabular Language Model

September 13, 2023

September 12, 2023

September 9, 2023

Exploring Robust Features for Improving Adversarial Robustness
Hong Wang, Yuefan Deng, Shinjae Yoo, Yuewei Lin
Adversarial Attack Adversarial Example Adversarial Robustness Adversarial Perturbation

September 7, 2023

How adversarial attacks can disrupt seemingly stable accurate classifiers
Oliver J. Sutton, Qinghua Zhou, Ivan Y. Tyukin, Alexander N. Gorban, Alexander Bastounis, Desmond J. Higham
Adversarial Attack Adversarial Example Adversarial Perturbation Adversarial Risk Stable Classifier

September 4, 2023

September 3, 2023

Robust and Efficient Interference Neural Networks for Defending Against Adversarial Attacks in ImageNet
Yunuo Xiong, Shujuan Liu, Hongwei Xiong
Adversarial Attack Adversarial Example Adversarial Training Supervised ImageNet Robust Version Adversarial Image Catastrophic Interference

September 2, 2023

Towards Certified Probabilistic Robustness with High Accuracy
Ruihan Zhang, Peixin Zhang, Jun Sun
Adversarial Example Adversarial Training Model Robustness Robust Training High Accuracy Probabilistic Robustness

September 1, 2023

Curating Naturally Adversarial Datasets for Learning-Enabled Medical Cyber-Physical Systems
Sydney Pugh, Ivan Ruchkin, Insup Lee, James Weimer
Native Robustness Adversarial Example Adversarial Datasets Natural Adversarial Sample