Adversarial Transferability

Adversarial transferability explores how adversarial examples—inputs designed to fool machine learning models—can be generated for one model and successfully used to attack others, even those with different architectures or training data. Current research focuses on improving the effectiveness of these "transfer" attacks across various model types, including convolutional neural networks (CNNs), vision transformers (ViTs), graph neural networks (GNNs), and large language models (LLMs), often employing techniques like input transformations and gradient manipulation to enhance their generalization. Understanding and mitigating adversarial transferability is crucial for ensuring the robustness and security of AI systems in diverse applications, from image recognition to cybersecurity.

Papers

July 16, 2024

Enhancing TinyML Security: Study of Adversarial Attack Transferability
Parin Shah, Yuvaraj Govindarajulu, Pavan Kulkarni, Manojkumar Parmar
Adversarial Attack Study Feature TinyML Model Adversarial Vulnerability Embedded System Adversarial Transferability

July 11, 2024

Boosting Adversarial Transferability for Skeleton-based Action Recognition via Exploring the Model Posterior Space
Yunfeng Diao, Baiqi Wu, Ruixuan Zhang, Xun Yang, Meng Wang, He Wang
Action Recognition Skeleton Based Action Recognition Adversarial Transferability Bayesian Posterior Skeletal Motion

July 2, 2024

Looking From the Future: Multi-order Iterations Can Enhance Adversarial Attack Transferability
Zijian Ying, Qianmu Li, Tao Wang, Zhichao Lian, Shunmei Meng, Xuyun Zhang
Future Reasoning Attack Success Rate Transferable Attack Adversarial Transferability Adversarial Perspective

June 20, 2024

Explainable AI Security: Exploring Robustness of Graph Neural Networks to Adversarial Attacks
Tao Wu, Canyixing Cui, Xingping Xian, Shaojie Qiao, Chao Wang, Lin Yuan, Shui Yu
Graph Neural Network Adversarial Attack Native Robustness Adversarial Example Adversarial Robustness Adversarial Transferability Artificial Intelligence Security Robust Graph Neural Network

May 23, 2024

Learning to Transform Dynamically for Better Adversarial Transferability
Rongyi Zhu, Zeliang Zhang, Susan Liang, Zhuo Liu, Chenliang Xu
LeArning Abstract Adversarial Example Adversarial Sample Adversarial Transferability Model Attack

April 15, 2024

Black-box Adversarial Transferability: An Empirical Study in Cybersecurity Perspective
Khushnaseeb Roshan, Aasim Zafar
Adversarial Attack Empirical Study Cybersecurity Perspective Adversarial Transferability White Box Adversarial Attack

March 14, 2024

An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models
Haochen Luo, Jindong Gu, Fengyuan Liu, Philip Torr
Vision Language Model Adversarial Perturbation Complex Prompt Task Specific Model Adversarial Transferability

February 6, 2024

Boosting Adversarial Transferability across Model Genus by Deformation-Constrained Warping
Qinliang Lin, Cheng Luo, Zenghao Niu, Xilin He, Weicheng Xie, Yuanbo Hou, Linlin Shen, Siyang Song
Adversarial Example Adversarial Transferability Model Attack Warping Method Feature Warping

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

December 20, 2023

LRS: Enhancing Adversarial Transferability through Lipschitz Regularized Surrogate
Tao Wu, Tie Luo, Donald C. Wunsch
Adversarial Example Black Box Adversarial Transferability Lipschitz Regularization

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

November 28, 2023

Rethinking Mixup for Improving the Adversarial Transferability
Xiaosen Wang, Zeyuan Yin
Convolutional Neural Network Adversarial Example Spatio Temporal Mixup Mechanism Adversarial Transferability Local Mixup Mixup Augmentation

November 18, 2023

October 26, 2023

Unscrambling the Rectification of Adversarial Attacks Transferability across Computer Networks
Ehsan Nowroozi, Samaneh Ghelichkhani, Imran Haider, Ali Dehghantanha
Convolutional Neural Network Adversarial Attack Adversarial Example Adversarial Transferability Computer Network Noise Rectification Fast Gradient Sign Method

September 26, 2023

Structure Invariant Transformation for better Adversarial Transferability
Xiaosen Wang, Zeliang Zhang, Jianping Zhang
Adversarial Attack Adversarial Transferability Structural Attack Input Transformation Transfer Based Attack Effective Adversarial

September 19, 2023

Model Leeching: An Extraction Attack Targeting LLMs
Lewis Birch, William Hackett, Stefan Trawicki, Neeraj Suri, Peter Garraghan
Large Language Model Machine Learning Adversarial Transferability Extraction Attack Model Error

August 20, 2023

Boosting Adversarial Transferability by Block Shuffle and Rotation
Kunyu Wang, Xuanran He, Wenxuan Wang, Xiaosen Wang
Adversarial Example Rotation Angle Shuffle Model Adversarial Transferability Input Transformation Transfer Based Attack

July 1, 2023

Common Knowledge Learning for Generating Transferable Adversarial Examples
Ruijie Yang, Yuanfang Guo, Junfu Wang, Jiantao Zhou, Yunhong Wang
Adversarial Example Adversarial Transferability Transfer Based Adversarial Attack

June 28, 2023

Boosting Adversarial Transferability with Learnable Patch-wise Masks
Xingxing Wei, Shiji Zhao
Adversarial Example Adversarial Perturbation Adversarial Transferability Patch Wise Mask