Backdoor Injection

Backdoor injection attacks exploit vulnerabilities in machine learning models by subtly altering training data to trigger malicious behavior under specific, often hidden, input conditions. Current research focuses on developing increasingly sophisticated attacks targeting diverse model architectures, including convolutional neural networks, image-to-image networks, large language models, and diffusion models, often employing techniques like data poisoning, adversarial perturbations, and genetic algorithms to optimize trigger design and stealth. The significance of this research lies in its implications for the security and trustworthiness of AI systems across various applications, from autonomous driving to natural language processing, highlighting the urgent need for robust defense mechanisms.

Papers

July 30, 2024

DeepBaR: Fault Backdoor Attack on Deep Neural Network Layers
C. A. Martínez-Mejía, J. Solano, J. Breier, D. Bucko, X. Hou
Adversarial Sample CNN Architecture Neural Network Layer Backdoor Injection Fault Injection Attack Deep Attack

July 15, 2024

Backdoor Attacks against Image-to-Image Networks
Wenbo Jiang, Hongwei Li, Jiaming He, Rui Zhang, Guowen Xu, Tianwei Zhang, Rongxing Lu
Backdoor Attack Backdoor Defense Image to Image Backdoor Injection

May 9, 2024

Towards Robust Physical-world Backdoor Attacks on Lane Detection
Xinwei Zhang, Aishan Liu, Tianyuan Zhang, Siyuan Liang, Xianglong Liu
Autonomous Driving Dynamic Scene Lane Detection Backdoor Injection Adversarial Backdoor Physical Backdoor Attack

November 15, 2023

Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
Yuanpu Cao, Bochuan Cao, Jinghui Chen
Digital STEALTH Metric Misalignment State Backdoor Injection Alignment Breaking Attack

September 27, 2023

Genetic Algorithm-Based Dynamic Backdoor Attack on Federated Learning-Based Network Traffic Classification
Mahmoud Nazzal, Nura Aljaafari, Ahmed Sawalmeh, Abdallah Khreishah, Muhammad Anan, Abdulelah Algosaibi, Mohammed Alnaeem, Adel Aldalbahi, Abdulaziz Alhumam, Conrado P. Vizcarra, Shadan Alhamed
Backdoor Attack Federated Prompt Cooperation Backdoor Trigger Traffic Classification Backdoor Injection

June 14, 2023

Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
Ziqiang Li, Hong Sun, Pengfei Xia, Heng Li, Beihao Xia, Yi Wu, Bin Li
Deep Neural Network Backdoor Attack Real World Scenario Backdoor Injection

March 25, 2023

Backdoor Attacks with Input-unique Triggers in NLP
Xukun Zhou, Jiwei Li, Tianwei Zhang, Lingjuan Lyu, Muqiao Yang, Jun He
Natural Language Processing Backdoor Attack Backdoor Trigger Backdoor Injection Trigger Design Backdoor Policy

December 20, 2022

Flareon: Stealthy any2any Backdoor Injection via Poisoned Augmentation
Tianrui Qin, Xianghuan He, Xitong Gao, Yiren Zhao, Kejiang Ye, Cheng-Zhong Xu
Backdoor Attack Supply Chain Attack Success Rate Backdoor Injection

December 11, 2022

How to Backdoor Diffusion Models?
Sheng-Yen Chou, Pin-Yu Chen, Tsung-Yi Ho
Backdoor Attack Backdoor Injection Backdoor Model

September 29, 2022

Augmentation Backdoors
Joseph Rance, Yiren Zhao, Ilia Shumailov, Robert Mullins
Data Augmentation Backdoor Attack Augmentation Method Backdoor Injection Enhancement Attack

July 12, 2022

Backdoor Attacks on Crowd Counting
Yuhua Sun, Tailai Zhang, Xingjun Ma, Pan Zhou, Jian Lou, Zichuan Xu, Xing Di, Yu Cheng, Lichao
Backdoor Attack Crowd Counting Backdoor Poisoning Attack Backdoor Injection Crowd Counting Model

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

June 24, 2022

Defending Backdoor Attacks on Vision Transformer via Patch Processing
Khoa D. Doan, Yingjie Lao, Peng Yang, Ping Li
Convolutional Neural Network Vision Transformer Adversarial Example Backdoor Attack Backdoor Injection Mitigating Backdoor

June 10, 2022

Enhancing Clean Label Backdoor Attack with Two-phase Specific Triggers
Nan Luo, Yuanzhang Li, Yajie Wang, Shangbo Wu, Yu-an Tan, Quanxin Zhang
Backdoor Attack Digital STEALTH Metric Clean Label Backdoor Attack Backdoor Injection

January 31, 2022

Imperceptible and Multi-channel Backdoor Attack against Deep Neural Networks
Mingfu Xue, Shifeng Ni, Yinghao Wu, Yushu Zhang, Jian Wang, Weiqiang Liu
Deep Neural Network Backdoor Attack Steganographic Performance Imperceptible Pattern Backdoor Injection

January 24, 2022

Backdoor Defense with Machine Unlearning
Yang Liu, Mingyuan Fan, Cen Chen, Ximeng Liu, Zhuo Ma, Li Wang, Jianfeng Ma
Backdoor Attack Machine Unlearning Backdoor Defense Backdoor Injection