Transfer Based Adversarial Attack

Transfer-based adversarial attacks exploit the vulnerability of machine learning models by crafting adversarial examples using a surrogate model to attack a target model without direct access. Current research focuses on improving the transferability of these attacks across diverse model architectures (e.g., CNNs, Transformers) using techniques like model ensembles, adaptive transformations, and tailored loss functions to overcome differences in model architectures and decision boundaries. This research is crucial for understanding and mitigating the security risks posed by adversarial examples to various applications, including speech recognition, image classification, and even large language models, ultimately driving the development of more robust and secure AI systems.

Papers

October 26, 2024

Transferable Adversarial Attacks on SAM and Its Downstream Models
Song Xia, Wenhan Yang, Yi Yu, Xun Lin, Henghui Ding, Lingyu Duan, Xudong Jiang
Adversarial Attack Adversarial Example Segment Anything Model Transferable Adversarial Attack Adversarial Risk Downstream Model Transfer Based Adversarial Attack

June 27, 2024

Zero-Query Adversarial Attack on Black-box Automatic Speech Recognition Systems
Zheng Fang, Tao Wang, Lingchen Zhao, Shenyi Zhang, Bowen Li, Yunjie Ge, Qi Li, Chao Shen, Qian Wang
Adversarial Attack Adversarial Example Black Box Speech Recognition System Transfer Based Adversarial Attack MI Attack

May 9, 2024

Model Inversion Robustness: Can Transfer Learning Help?
Sy-Tuyen Ho, Koh Jun Hao, Keshigeyan Chandrasegaran, Ngoc-Bao Nguyen, Ngai-Man Cheung
Model Inversion Attack Model Inversion Transfer Based Adversarial Attack

September 18, 2023

Dual Student Networks for Data-Free Model Stealing
James Beetham, Navid Kardan, Ajmal Mian, Mubarak Shah
Model Free Model Gradient Model Stealing Training Compute Transfer Based Adversarial Attack Student Network

August 5, 2023

An Adaptive Model Ensemble Adversarial Attack for Boosting Adversarial Transferability
Bin Chen, Jia-Li Yin, Shukai Chen, Bo-Hao Chen, Ximeng Liu
Adversarial Example Ensemble Adversarial Transfer Based Adversarial Attack Ensemble 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

May 23, 2023

QFA2SR: Query-Free Adversarial Transfer Attacks to Speaker Recognition Systems
Guangke Chen, Yedi Zhang, Zhe Zhao, Fu Song
Adversarial Attack Black Box Attack Voice Assistant Speaker Recognition System Transfer Based Adversarial Attack

April 14, 2023

Generating Adversarial Examples with Better Transferability via Masking Unimportant Parameters of Surrogate Model
Dingcheng Yang, Wenjian Yu, Zihao Xiao, Jiaqi Luo
Adversarial Example Surrogate Model Task Transferability Importance Score Transfer Based Adversarial Attack Transfer Based Attack

March 27, 2023

Improving the Transferability of Adversarial Examples via Direction Tuning
Xiangyuan Yang, Jie Lin, Hanlin Zhang, Xinyu Yang, Peng Zhao
Adversarial Example Task Transferability Gradient Based Attack Transfer Attack Transfer Based Adversarial Attack

March 16, 2023

Rethinking Model Ensemble in Transfer-based Adversarial Attacks
Huanran Chen, Yichi Zhang, Yinpeng Dong, Xiao Yang, Hang Su, Jun Zhu
Adversarial Attack Adversarial Example Model Ensemble Adversarial Prediction Transfer Based Adversarial Attack

November 17, 2022

Towards Good Practices in Evaluating Transfer Adversarial Attacks
Zhengyu Zhao, Hanwei Zhang, Renjue Li, Ronan Sicre, Laurent Amsaleg, Michael Backes
Adversarial Attack Best Practice Transfer Attack Transfer Based Adversarial Attack Optimal Attack

November 27, 2021

Adaptive Image Transformations for Transfer-based Adversarial Attack
Zheng Yuan, Jie Zhang, Shiguang Shan
Adversarial Attack Adversarial Example Black Box Image Transformation Transfer Based Adversarial Attack