Adversarial Purification

Adversarial purification aims to remove malicious perturbations from data inputs, thereby improving the robustness of machine learning models against adversarial attacks without modifying the underlying classifier. Current research heavily utilizes diffusion models and generative adversarial networks (GANs), often incorporating techniques like classifier guidance and adaptive noise control to enhance purification accuracy and efficiency, particularly for image and text data. This field is crucial for bolstering the reliability and security of AI systems across diverse applications, from mobile device security to intrusion detection and power system monitoring, by mitigating the impact of increasingly sophisticated adversarial attacks.

Papers

September 23, 2024

Improving Adversarial Robustness for 3D Point Cloud Recognition at Test-Time through Purified Self-Training
Jinpeng Lin, Xulei Yang, Tianrui Li, Xun Xu
Adversarial Attack Adversarial Training Adversarial Robustness Self Training Adversarial Sample Test Time Adversarial Purification Point Cloud Recognition

September 12, 2024

High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image Synthesis
Takuto Onikubo, Yusuke Matsui
Image Synthesis Adversarial Noise Adversarial Image Robust Defense Adversarial Purification

August 31, 2024

LightPure: Realtime Adversarial Image Purification for Mobile Devices Using Diffusion Models
Hossein Khalili, Seongbin Park, Vincent Li, Brandan Bright, Ali Payani, Ramana Rao Kompella, Nader Sehatbakhsh
Diffusion Model Adversarial Training Adversarial Robustness Mobile Device Adversarial Purification Adversarial Machine Learning One Shot Generative

August 12, 2024

Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information
Mingkun Zhang, Jianing Li, Wei Chen, Jiafeng Guo, Xueqi Cheng
Adversarial Attack Adversarial Example Adversarial Robustness Adversarial Purification Classifier Guidance

August 1, 2024

ADBM: Adversarial diffusion bridge model for reliable adversarial purification
Xiao Li, Wenxuan Sun, Huanran Chen, Qiongxiu Li, Yining Liu, Yingzhe He, Jie Shi, Xiaolin Hu
Adversarial Example Adversarial Data Adversarial Purification Adversarial Diffusion

June 25, 2024

Diffusion-based Adversarial Purification for Intrusion Detection
Mohamed Amine Merzouk, Erwan Beurier, Reda Yaich, Nora Boulahia-Cuppens, Frédéric Cuppens
Diffusion Model Adversarial Attack Adversarial Example Adversarial Robustness Intrusion Detection Adversarial Purification

June 5, 2024

ZeroPur: Succinct Training-Free Adversarial Purification
Xiuli Bi, Zonglin Yang, Bo Liu, Xiaodong Cun, Chi-Man Pun, Pietro Lio, Bin Xiao
Adversarial Attack Adversarial Example Adversarial Image Adversarial Purification

April 22, 2024

Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective
Yiming Liu, Kezhao Liu, Yao Xiao, Ziyi Dong, Xiaogang Xu, Pengxu Wei, Liang Lin
Adversarial Attack Adversarial Perturbation Denoising Diffusion Adversarial Purification Diffusion Purification

April 10, 2024

Adversarial purification for no-reference image-quality metrics: applicability study and new methods
Aleksandr Gushchin, Anna Chistyakova, Vladislav Minashkin, Anastasia Antsiferova, Dmitriy Vatolin
Adversarial Attack New Method Reference Image Quality Assessment Adversarial Purification Nr Iqa Applicability Study Image Quality Metric

March 24, 2024

Robust Diffusion Models for Adversarial Purification
Guang Lin, Zerui Tao, Jianhai Zhang, Toshihisa Tanaka, Qibin Zhao
Diffusion Model Adversarial Attack Pre Trained Diffusion Model Adversarial Purification

March 18, 2024

Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM
Linyu Tang, Lei Zhang
Adversarial Attack Adversarial Robustness Artefact PARTICLE Adversarial Purification Robust Overfitting Fast Gradient Sign Method

February 21, 2024

Adversarial Purification and Fine-tuning for Robust UDC Image Restoration
Zhenbo Song, Zhenyuan Zhang, Kaihao Zhang, Zhaoxin Fan, Jianfeng Lu
Fine Tuning Image Degradation Adversarial Purification Display Camera

February 5, 2024

Adversarial Text Purification: A Large Language Model Approach for Defense
Raha Moraffah, Shubh Khandelwal, Amrita Bhattacharjee, Huan Liu
Large Language Model Adversarial Text Adversarial Purification Adversarial Text Purification

January 29, 2024

Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization
Guang Lin, Chao Li, Jianhai Zhang, Toshihisa Tanaka, Qibin Zhao
Native Robustness Strong Generalization Adversarial Training Adversarial Purification Diffusion Purification

January 19, 2024

PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks
Ping Guo, Zhiyuan Yang, Xi Lin, Qingchuan Zhao, Qingfu Zhang
Adversarial Example Black Box Adversarial Purification Diffusion Purification QuEry Based Attack Purification Model

December 11, 2023

MalPurifier: Enhancing Android Malware Detection with Adversarial Purification against Evasion Attacks
Yuyang Zhou, Guang Cheng, Zongyao Chen, Shui Yu
Android Malware Adversarial Purification Evasion Attack Malware Datasets

December 8, 2023

MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model
Kaiyu Song, Hanjiang Lai
Adversarial Perturbation Adversarial Purification

November 26, 2023

Adversarial Purification of Information Masking
Sitong Liu, Zhichao Lian, Shuangquan Zhang, Liang Xiao
Adversarial Perturbation Adversarial Purification Clean Data Informational Masking

November 22, 2023

Diffusion models meet image counter-forensics
Matías Tailanian, Marina Gardella, Álvaro Pardo, Pablo Musé
Diffusion Model Adversarial Purification Forensic Application Diffusion Purification Video Forensics

November 13, 2023

Adversarial Purification for Data-Driven Power System Event Classifiers with Diffusion Models
Yuanbin Cheng, Koji Yamashita, Jim Follum, Nanpeng Yu
Diffusion Model Adversarial Purification Phasor Measurement Unit Power Quality

Adversarial Purification

Papers

Improving Adversarial Robustness for 3D Point Cloud Recognition at Test-Time through Purified Self-Training

High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image Synthesis

LightPure: Realtime Adversarial Image Purification for Mobile Devices Using Diffusion Models

Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information

ADBM: Adversarial diffusion bridge model for reliable adversarial purification

Diffusion-based Adversarial Purification for Intrusion Detection

ZeroPur: Succinct Training-Free Adversarial Purification

Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective

Adversarial purification for no-reference image-quality metrics: applicability study and new methods

Robust Diffusion Models for Adversarial Purification

Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM

Adversarial Purification and Fine-tuning for Robust UDC Image Restoration

Adversarial Text Purification: A Large Language Model Approach for Defense

Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization

PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks

MalPurifier: Enhancing Android Malware Detection with Adversarial Purification against Evasion Attacks

MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Model

Adversarial Purification of Information Masking

Diffusion models meet image counter-forensics

Adversarial Purification for Data-Driven Power System Event Classifiers with Diffusion Models