Transfer Attack

Transfer attacks exploit the vulnerability of machine learning models by crafting adversarial examples on one model (the surrogate) and then using these examples to fool other, unseen models (the victims). Current research focuses on improving the transferability of these attacks across diverse model architectures, including vision-language models and object detectors, often employing techniques like bilevel optimization, gradient manipulation, and prompt engineering to enhance their effectiveness. This area is crucial because successful transfer attacks highlight significant security risks in real-world applications of machine learning, particularly in black-box settings where model details are unavailable to the attacker, and motivates the development of more robust and secure models.

Papers

July 30, 2024

Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks
Hunmin Yang, Jongoh Jeong, Kuk-Jin Yoon
Contrastive Learning Adversarial Example Adversarial Perturbation Transferable Adversarial Attack Transfer Attack Generative Attack

July 21, 2024

When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?
Rylan Schaeffer, Dan Valentine, Luke Bailey, James Chua, Cristóbal Eyzaguirre, Zane Durante, Joe Benton, Brando Miranda, Henry Sleight, John Hughes, Rajashree Agrawal, Mrinank Sharma, Scott Emmons, Sanmi Koyejo, Ethan Perez
Vision Language Model Jailbreak Attack Transferable Adversarial Attack Transfer Attack Vision Backbone

June 12, 2024

Transferable Embedding Inversion Attack: Uncovering Privacy Risks in Text Embeddings without Model Queries
Yu-Hsiang Huang, Yuche Tsai, Hsiang Hsiao, Hong-Yi Lin, Shou-De Lin
Text Embeddings Privacy Risk Transfer Attack Inversion Attack Model Join

June 4, 2024

Advancing Generalized Transfer Attack with Initialization Derived Bilevel Optimization and Dynamic Sequence Truncation
Yaohua Liu, Jiaxin Gao, Xuan Liu, Xianghao Jiao, Xin Fan, Risheng Liu
Adversarial Example Surrogate Model Bilevel Optimization Pseudo Victim AttackER Transfer Attack Sequence Length Reduction

May 25, 2024

Enhancing Adversarial Transferability Through Neighborhood Conditional Sampling
Chunlin Qiu, Yiheng Duan, Lingchen Zhao, Qian Wang
Adversarial Example Transfer Attack Adversarial Region

February 26, 2024

Investigating Deep Watermark Security: An Adversarial Transferability Perspective
Biqing Qi, Junqi Gao, Yiang Luo, Jianxing Liu, Ligang Wu, Bowen Zhou
Transferable Adversarial Attack Transfer Attack Deep Watermarking

December 15, 2023

LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer
Yuxin Cao, Ziyu Zhao, Xi Xiao, Derui Wang, Minhui Xue, Jin Lu
Adversarial Example Style Transfer Video Recognition Transfer Attack Replay Attack Harmless Logo Patch Based Attack Certifiable Patch Defense

November 22, 2023

Transfer Attacks and Defenses for Large Language Models on Coding Tasks
Chi Zhang, Zifan Wang, Ravi Mangal, Matt Fredrikson, Limin Jia, Corina Pasareanu
Adversarial Example Adversarial Perturbation Programming Task Prompt Based Transfer Attack Code Vulnerability

October 26, 2023

PubDef: Defending Against Transfer Attacks From Public Models
Chawin Sitawarin, Jaewon Chang, David Huang, Wesson Altoyan, David Wagner
Adversarial Attack White Box Transfer Attack White Box Adversarial Attack Public Model

July 9, 2023

GNP Attack: Transferable Adversarial Examples via Gradient Norm Penalty
Tao Wu, Tie Luo, Donald C. Wunsch
Adversarial Example Black Box Model Black Box Attack Transfer Attack Norm Penalty

June 22, 2023

Rethinking the Backward Propagation for Adversarial Transferability
Xiaosen Wang, Kangheng Tong, Kun He
Adversarial Example Backward Propagation Transfer 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

November 21, 2022

Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization
Jiafeng Wang, Zhaoyu Chen, Kaixun Jiang, Dingkang Yang, Lingyi Hong, Pinxue Guo, Haijing Guo, Wenqiang Zhang
Adversarial Attack Adversarial Example Task Transferability Gradient Based Optimization Transfer Attack Gradient Vanishing

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

August 23, 2022

Transferability Ranking of Adversarial Examples
Mosh Levy, Guy Amit, Yuval Elovici, Yisroel Mirsky
Adversarial Example Black Box Adversarial Transferability Transfer Attack Transferability Score

June 15, 2022

Hardening DNNs against Transfer Attacks during Network Compression using Greedy Adversarial Pruning
Jonah O'Brien Weiss, Tiago Alves, Sandip Kundu
Adversarial Robustness DNN Framework Adversarial Input Neural Network Compression Network Compression Transfer Attack Adversarial Pruning

April 7, 2022

Transfer Attacks Revisited: A Large-Scale Empirical Study in Real Computer Vision Settings
Yuhao Mao, Chong Fu, Saizhuo Wang, Shouling Ji, Xuhong Zhang, Zhenguang Liu, Jun Zhou, Alex X. Liu, Raheem Beyah, Ting Wang
Adversarial Attack Transferable Attack Transfer Attack

March 29, 2022

Zero-Query Transfer Attacks on Context-Aware Object Detectors
Zikui Cai, Shantanu Rane, Alejandro E. Brito, Chengyu Song, Srikanth V. Krishnamurthy, Amit K. Roy-Chowdhury, M. Salman Asif
Adversarial Attack Adversarial Perturbation Transfer Attack Context Driven Contextual Attack

March 16, 2022

Attacking deep networks with surrogate-based adversarial black-box methods is easy
Nicholas A. Lord, Romain Mueller, Luca Bertinetto
Adversarial Attack Deep Network Surrogate Model Transfer Attack Surrogate Neural Network

December 10, 2021

Learning to Learn Transferable Attack
Shuman Fang, Jie Li, Xianming Lin, Rongrong Ji
LeArning Abstract Adversarial Attack Adversarial Perturbation Transferable Attack Transfer Attack Model Augmentation