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

April 14, 2023

April 13, 2023

April 11, 2023

April 10, 2023

Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence
Hanbin Hong, Xinyu Zhang, Binghui Wang, Zhongjie Ba, Yuan Hong
Adversarial Attack Adversarial Example Attack Success Rate

April 6, 2023

Robust Neural Architecture Search
Xunyu Zhu, Jian Li, Yong Liu, Weiping Wang
Adversarial Attack Adversarial Example Neural Architecture Search Robust Neural Architecture Search

April 5, 2023

April 3, 2023

Model-Agnostic Reachability Analysis on Deep Neural Networks
Chi Zhang, Wenjie Ruan, Fu Wang, Peipei Xu, Geyong Min, Xiaowei Huang
Deep Neural Network Adversarial Example Reachability Analysis Verification Framework Verification Strategy

April 1, 2023

Improving Fast Adversarial Training with Prior-Guided Knowledge
Xiaojun Jia, Yong Zhang, Xingxing Wei, Baoyuan Wu, Ke Ma, Jue Wang, Xiaochun Cao
Adversarial Example Adversarial Perturbation Fast Adversarial Training

March 29, 2023

Latent Feature Relation Consistency for Adversarial Robustness
Xingbin Liu, Huafeng Kuang, Hong Liu, Xianming Lin, Yongjian Wu, Rongrong Ji
Deep Neural Network Adversarial Example Adversarial Robustness DNN Framework Latent Feature Imperceptible Adversarial Perturbation Latent Consistency Model

March 28, 2023

TransAudio: Towards the Transferable Adversarial Audio Attack via Learning Contextualized Perturbations
Qi Gege, Yuefeng Chen, Xiaofeng Mao, Yao Zhu, Binyuan Hui, Xiaodan Li, Rong Zhang, Hui Xue
Adversarial Example Transferable Attack Adversarial Audio Word Level Attack Transfer Based Attack Context Perturbation

March 27, 2023

March 25, 2023

March 24, 2023

Adversarial Example

Papers

Interpretability is a Kind of Safety: An Interpreter-based Ensemble for Adversary Defense

Generating Adversarial Examples with Better Transferability via Masking Unimportant Parameters of Surrogate Model

False Claims against Model Ownership Resolution

Adversarial Examples from Dimensional Invariance

Boosting Cross-task Transferability of Adversarial Patches with Visual Relations

Simultaneous Adversarial Attacks On Multiple Face Recognition System Components

Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence

Robust Neural Architecture Search

Going Further: Flatness at the Rescue of Early Stopping for Adversarial Example Transferability

How to choose your best allies for a transferable attack?

Model-Agnostic Reachability Analysis on Deep Neural Networks

Improving Fast Adversarial Training with Prior-Guided Knowledge

Latent Feature Relation Consistency for Adversarial Robustness

TransAudio: Towards the Transferable Adversarial Audio Attack via Learning Contextualized Perturbations

Personalized Federated Learning on Long-Tailed Data via Adversarial Feature Augmentation

Improving the Transferability of Adversarial Examples via Direction Tuning

AdvCheck: Characterizing Adversarial Examples via Local Gradient Checking

CFA: Class-wise Calibrated Fair Adversarial Training

How many dimensions are required to find an adversarial example?

Adversarial Attack and Defense for Medical Image Analysis: Methods and Applications