Invisible Backdoor Attack

Invisible backdoor attacks exploit vulnerabilities in machine learning models to introduce malicious functionality without noticeable alterations to the model's normal behavior. Current research focuses on developing increasingly stealthy attacks, employing techniques like steganography, generative adversarial networks, and manipulation of semantic or frequency-domain features to embed triggers within data or model parameters across various architectures, including diffusion models and federated learning systems. This research is crucial because these attacks can compromise the security and reliability of AI systems in diverse applications, ranging from image classification and object detection to cross-modal learning and person re-identification, necessitating the development of robust defenses.

Papers

October 3, 2024

BadCM: Invisible Backdoor Attack Against Cross-Modal Learning
Zheng Zhang, Xu Yuan, Lei Zhu, Jingkuan Song, Liqiang Nie
Cross Modal Modal Attack Man in the Middle Attack Invisible Backdoor Attack Multimodal Backdoor

June 2, 2024

Invisible Backdoor Attacks on Diffusion Models
Sen Li, Junchi Ma, Minhao Cheng
Diffusion Model Backdoor Attack Model Watermarking Invisible Backdoor Attack

May 19, 2024

An Invisible Backdoor Attack Based On Semantic Feature
Yangming Chen
Deep Neural Network Backdoor Attack Backdoor Defense Semantic Feature Attack Success Rate Invisible Backdoor Attack

April 22, 2024

Dual Model Replacement:invisible Multi-target Backdoor Attack based on Federal Learning
Rong Wang, Guichen Zhou, Mingjun Gao, Yunpeng Xiao
Backdoor Attack Neural Backdoor Invisible Backdoor Attack Multimodal Backdoor

March 20, 2024

Mask-based Invisible Backdoor Attacks on Object Detection
Jeongjin Shin
Backdoor Attack Invisible Backdoor Attack Object Generation Attack

March 18, 2024

Invisible Backdoor Attack Through Singular Value Decomposition
Wenmin Chen, Xiaowei Xu
Backdoor Attack Singular Value Decomposition Defense Method Invisible Backdoor Attack

October 1, 2023

GhostEncoder: Stealthy Backdoor Attacks with Dynamic Triggers to Pre-trained Encoders in Self-supervised Learning
Qiannan Wang, Changchun Yin, Zhe Liu, Liming Fang, Run Wang, Chenhao Lin
Self Supervised Learning Backdoor Attack Encoder Side Stealthy Backdoor Attack Backdoor Sample Invisible Backdoor Attack Trigger Design

May 11, 2023

Backdoor Attack with Sparse and Invisible Trigger
Yinghua Gao, Yiming Li, Xueluan Gong, Zhifeng Li, Shu-Tao Xia, Qian Wang
Deep Neural Network Backdoor Attack Many Sparse Backdoor Defense Invisible Backdoor Attack Imperceptible Trigger

February 25, 2023

SATBA: An Invisible Backdoor Attack Based On Spatial Attention
Huasong Zhou, Xiaowei Xu, Xiaodong Wang, Leon Bevan Bullock
Backdoor Attack Backdoor Defense Spatial Attention Invisible Backdoor Attack

November 20, 2022

Invisible Backdoor Attack with Dynamic Triggers against Person Re-identification
Wenli Sun, Xinyang Jiang, Shuguang Dou, Dongsheng Li, Duoqian Miao, Cheng Deng, Cairong Zhao
Adversarial Attack Backdoor Attack Person Re Identification Invisible Backdoor Attack Trigger Design

July 26, 2022

FRIB: Low-poisoning Rate Invisible Backdoor Attack based on Feature Repair
Hui Xia, Xiugui Yang, Xiangyun Qian, Rui Zhang
Backdoor Attack Invisible Backdoor Attack Blind Watermarking

July 9, 2022

Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain
Chang Yue, Peizhuo Lv, Ruigang Liang, Kai Chen
Backdoor Attack Frequency Domain Data Poisoning Backdoor Injection Invisible Backdoor Attack

July 1, 2022

BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label
Shengshan Hu, Ziqi Zhou, Yechao Zhang, Leo Yu Zhang, Yifeng Zheng, Yuanyuan HE, Hai Jin
Adversarial Attack Backdoor Attack Deep Hashing Adversarial Backdoor Invisible Backdoor Attack Clean Label Image Backdoor Attack