Transferable Adversarial Attack

Transferable adversarial attacks aim to create perturbations in input data that fool multiple machine learning models, even those unseen during the attack's design. Current research focuses on improving the transferability of these attacks across diverse model architectures (including Vision Transformers, GANs, and diffusion models) and tasks (e.g., image classification, object detection, and language modeling), often employing techniques like gradient editing, contrastive learning, and frequency-domain manipulation. This research is crucial for evaluating the robustness of machine learning systems and informing the development of more secure and reliable AI applications, particularly in safety-critical domains.

Papers

February 1, 2024

Benchmarking Transferable Adversarial Attacks
Zhibo Jin, Jiayu Zhang, Zhiyu Zhu, Huaming Chen
Adversarial Attack Native Robustness Deep Learning Model Transferable Adversarial Attack Adversarial Transferability

January 11, 2024

GE-AdvGAN: Improving the transferability of adversarial samples by gradient editing-based adversarial generative model
Zhiyu Zhu, Huaming Chen, Xinyi Wang, Jiayu Zhang, Zhibo Jin, Kim-Kwang Raymond Choo, Jun Shen, Dong Yuan
Generative Adversarial Network Adversarial Example Task Transferability Adversarial Sample Transferable Adversarial Attack

December 11, 2023

Towards Transferable Adversarial Attacks with Centralized Perturbation
Shangbo Wu, Yu-an Tan, Yajie Wang, Ruinan Ma, Wencong Ma, Yuanzhang Li
Adversarial Perturbation Transferable Attack Transferable Adversarial Attack Adversarial Transferability

October 19, 2023

ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks
Xiaodong Yu, Hao Cheng, Xiaodong Liu, Dan Roth, Jianfeng Gao
Large Language Model Adversarial Example Retrieval Augmentation Transferable Adversarial Attack Hallucination Evaluation

October 1, 2023

Understanding Adversarial Transferability in Federated Learning
Yijiang Li, Ying Gao, Haohan Wang
Native Robustness Federated Learning Transferable Adversarial Attack Decentralized Training Federated Learning Application

September 19, 2023

Transferable Adversarial Attack on Image Tampering Localization
Yuqi Wang, Gang Cao, Zijie Lou, Haochen Zhu
Adversarial Attack Adversarial Example Transferable Adversarial Attack Tamper Detection Image Forgery Localization

August 30, 2023

Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models
Takami Sato, Justin Yue, Nanze Chen, Ningfei Wang, Qi Alfred Chen
Diffusion Model Empirical Study Denoising Diffusion Transferable Adversarial Attack Text to Image Generative Model Intriguing Property Diffusion Attack

July 27, 2023

Universal and Transferable Adversarial Attacks on Aligned Language Models
Andy Zou, Zifan Wang, Nicholas Carlini, Milad Nasr, J. Zico Kolter, Matt Fredrikson
Language Model Adversarial Attack Adversarial Prompt Universal Image Transferable Adversarial Attack Adversarial Suffix

July 6, 2023

Sampling-based Fast Gradient Rescaling Method for Highly Transferable Adversarial Attacks
Xu Han, Anmin Liu, Chenxuan Yao, Yanbo Fan, Kun He
Adversarial Example Practical Method Transferable Adversarial Attack Gradient Based Attack Gradient Update Fast Gradient

May 14, 2023

Diffusion Models for Imperceptible and Transferable Adversarial Attack
Jianqi Chen, Hao Chen, Keyan Chen, Yilan Zhang, Zhengxia Zou, Zhenwei Shi
Diffusion Model Adversarial Attack Adversarial Example Transferable Attack Transferable Adversarial Attack Imperceptible Pattern

March 28, 2023

Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularization
Jianping Zhang, Yizhan Huang, Weibin Wu, Michael R. Lyu
Vision Transformer Adversarial Sample Transferable Adversarial Attack Gradient Backpropagation Input Gradient Token Level Gradient

March 22, 2023

Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face Recognition
Zexin Li, Bangjie Yin, Taiping Yao, Juefeng Guo, Shouhong Ding, Simin Chen, Cong Liu
Multi Task Face Recognition Transferable Adversarial Attack

March 7, 2023

Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibration
Juanjuan Weng, Zhiming Luo, Zhun Zhong, Shaozi Li, Nicu Sebe
Adversarial Example Loss Function Cross Entropy Loss Adversarial Sample Transferable Adversarial Attack Logit Calibration Adaptive Margin

November 16, 2022

T-SEA: Transfer-based Self-Ensemble Attack on Object Detection
Hao Huang, Ziyan Chen, Huanran Chen, Yongtao Wang, Kevin Zhang
Black Box Transferable Attack Transferable Adversarial Attack Ensemble Attack

October 13, 2022

Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face Recognition
Shuai Jia, Bangjie Yin, Taiping Yao, Shouhong Ding, Chunhua Shen, Xiaokang Yang, Chao Ma
Adversarial Attack Face Recognition Adversarial Noise Rich Attribute Transferable Adversarial Attack Adversarial Feature Attribute Selection

October 9, 2022

Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspective
Yao Zhu, Yuefeng Chen, Xiaodan Li, Kejiang Chen, Yuan He, Xiang Tian, Bolun Zheng, Yaowu Chen, Qingming Huang
Adversarial Attack Adversarial Example Human Understanding Transferable Adversarial Attack Distributional Perspective

September 24, 2022

Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning
Zhengwei Fang, Rui Wang, Tao Huang, Liping Jing
Adversarial Example Adversarial Perturbation Transferable Adversarial Attack Perturbation Attack Normality Learning

August 11, 2022

Diverse Generative Perturbations on Attention Space for Transferable Adversarial Attacks
Woo Jae Kim, Seunghoon Hong, Sung-Eui Yoon
Adversarial Attack Adversarial Example Adversarial Perturbation Transferable Attack Transferable Adversarial Attack Hidden Representation Perturbation Visual Space

July 18, 2022

Adversarial Pixel Restoration as a Pretext Task for Transferable Perturbations
Hashmat Shadab Malik, Shahina K Kunhimon, Muzammal Naseer, Salman Khan, Fahad Shahbaz Khan
Additive Perturbation Transferable Adversarial Attack Adversarial Objective Pretext Task Deep Surrogate Restoration Network

May 26, 2022

Transferable Adversarial Attack based on Integrated Gradients
Yi Huang, Adams Wai-Kin Kong
Adversarial Example Task Transferability Transferable Attack Transferable Adversarial Attack Integrated Gradient

Transferable Adversarial Attack

Papers

Benchmarking Transferable Adversarial Attacks

GE-AdvGAN: Improving the transferability of adversarial samples by gradient editing-based adversarial generative model

Towards Transferable Adversarial Attacks with Centralized Perturbation

ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks

Understanding Adversarial Transferability in Federated Learning

Transferable Adversarial Attack on Image Tampering Localization

Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models

Universal and Transferable Adversarial Attacks on Aligned Language Models

Sampling-based Fast Gradient Rescaling Method for Highly Transferable Adversarial Attacks

Diffusion Models for Imperceptible and Transferable Adversarial Attack

Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularization

Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face Recognition

Logit Margin Matters: Improving Transferable Targeted Adversarial Attack by Logit Calibration

T-SEA: Transfer-based Self-Ensemble Attack on Object Detection

Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face Recognition

Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspective

Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning

Diverse Generative Perturbations on Attention Space for Transferable Adversarial Attacks

Adversarial Pixel Restoration as a Pretext Task for Transferable Perturbations

Transferable Adversarial Attack based on Integrated Gradients