Effective Backdoor Attack

Effective backdoor attacks aim to surreptitiously manipulate machine learning models, causing them to misbehave only when presented with specific triggers while maintaining normal functionality otherwise. Current research focuses on developing increasingly stealthy attacks targeting various model architectures, including large language models, federated learning systems, and even self-supervised models, often employing techniques like imperceptible triggers and prompt engineering to evade detection. The ability to launch such attacks highlights critical vulnerabilities in AI systems, underscoring the need for robust defenses and raising significant concerns about the security and trustworthiness of deployed AI models across diverse applications.

Papers

October 15, 2024

Backdoor Attack on Vertical Federated Graph Neural Network Learning
Jirui Yang, Peng Chen, Zhihui Lu, Ruijun Deng, Qiang Duan, Jianping Zeng
Backdoor Attack Effective Backdoor Attack Federated Graph Neural Network

August 14, 2024

BAPLe: Backdoor Attacks on Medical Foundational Models using Prompt Learning
Asif Hanif, Fahad Shamshad, Muhammad Awais, Muzammal Naseer, Fahad Shahbaz Khan, Karthik Nandakumar, Salman Khan, Rao Muhammad Anwer
Foundation Model Backdoor Attack Prompt Learning Image Text Effective Backdoor Attack

July 4, 2024

Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs
Sara Price, Arjun Panickssery, Sam Bowman, Asa Cooper Stickland
Large Language Model Backdoor Attack Backdoor Trigger Event Prediction Effective Backdoor Attack Hidden Backdoor

July 3, 2024

Venomancer: Towards Imperceptible and Target-on-Demand Backdoor Attacks in Federated Learning
Son Nguyen, Thinh Nguyen, Khoa D Doan, Kok-Seng Wong
Backdoor Attack Backdoor Trigger Effective Backdoor Attack Imperceptible Pattern

June 10, 2024

Lurking in the shadows: Unveiling Stealthy Backdoor Attacks against Personalized Federated Learning
Xiaoting Lyu, Yufei Han, Wei Wang, Jingkai Liu, Yongsheng Zhu, Guangquan Xu, Jiqiang Liu, Xiangliang Zhang
Backdoor Attack Personalized Federated Learning Quantum Shadow Stealthy Backdoor Attack Effective Backdoor Attack Hidden Backdoor Backdoor Threat

May 27, 2024

TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models
Yuzhou. Nie, Yanting. Wang, Jinyuan. Jia, Michael J. De Lucia, Nathaniel D. Bastian, Wenbo. Guo, Dawn. Song
Foundation Model Backdoor Attack Effective Backdoor Attack Task Agnostic Backdoor

May 23, 2024

Towards Imperceptible Backdoor Attack in Self-supervised Learning
Hanrong Zhang, Zhenting Wang, Tingxu Han, Mingyu Jin, Chenlu Zhan, Mengnan Du, Hongwei Wang, Shiqing Ma
Self Supervised Learning Backdoor Attack Backdoor Defense Effective Backdoor Attack Imperceptible Trigger

May 19, 2024

BOSC: A Backdoor-based Framework for Open Set Synthetic Image Attribution
Jun Wang, Benedetta Tondi, Mauro Barni
Synthetic Image Open Set Effective Backdoor Attack

November 28, 2023

Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
Ming-Yu Chung, Sheng-Yen Chou, Chia-Mu Yu, Pin-Yu Chen, Sy-Yen Kuo, Tsung-Yi Ho
Backdoor Attack Dataset Distillation Kernel Method Effective Backdoor Attack Trigger Design Resilient Backdoor

October 16, 2023

Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
Ganghua Wang, Xun Xian, Jayanth Srinivasa, Ashish Kundu, Xuan Bi, Mingyi Hong, Jie Ding
Backdoor Attack Backdoor Poisoning Attack Effective Backdoor Attack Backdoor Data

August 21, 2023

Temporal-Distributed Backdoor Attack Against Video Based Action Recognition
Xi Li, Songhe Wang, Ruiquan Huang, Mahanth Gowda, George Kesidis
Backdoor Attack Action Recognition Sign Language Recognition Effective Backdoor Attack Video Recognition Benchmark

July 19, 2023

Attacking by Aligning: Clean-Label Backdoor Attacks on Object Detection
Yize Cheng, Wenbin Hu, Minhao Cheng
Backdoor Attack Alignment Problem Deep Learning Based Object Clean Label Backdoor Attack Effective Backdoor Attack Object Generation Attack

June 14, 2023

A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks
Ziqiang Li, Hong Sun, Pengfei Xia, Beihao Xia, Xue Rui, Wei Zhang, Qinglang Guo, Bin Li
Backdoor Attack Backdoor Poisoning Attack Effective Backdoor Attack Weapon of Mass Destruction Proxy Poisoning Efficiency

March 1, 2023

Single Image Backdoor Inversion via Robust Smoothed Classifiers
Mingjie Sun, J. Zico Kolter
Smoothed Classifier Effective Backdoor Attack Resilient Backdoor Backdoor Inversion

February 11, 2023

Unnoticeable Backdoor Attacks on Graph Neural Networks
Enyan Dai, Minhua Lin, Xiang Zhang, Suhang Wang
Graph Neural Network Adversarial Attack Backdoor Attack Effective Backdoor Attack Graph Backdoor Attack

December 20, 2022

VSVC: Backdoor attack against Keyword Spotting based on Voiceprint Selection and Voice Conversion
Hanbo Cai, Pengcheng Zhang, Hai Dong, Yan Xiao, Shunhui Ji
Backdoor Attack Voice Conversion Keyword Spotting Effective Backdoor Attack Voice Activated

November 16, 2022

PBSM: Backdoor attack against Keyword spotting based on pitch boosting and sound masking
Hanbo Cai, Pengcheng Zhang, Hai Dong, Yan Xiao, Shunhui Ji
Backdoor Attack Keyword Enrollment Effective Backdoor Attack Noise Masking

August 13, 2022

Confidence Matters: Inspecting Backdoors in Deep Neural Networks via Distribution Transfer
Tong Wang, Yuan Yao, Feng Xu, Miao Xu, Shengwei An, Ting Wang
Deep Neural Network Backdoor Attack Formality Transfer Backdoor Trigger Confidence Aware Effective Backdoor Attack

November 22, 2021

Backdoor Attack through Frequency Domain
Tong Wang, Yuan Yao, Feng Xu, Shengwei An, Hanghang Tong, Ting Wang
Backdoor Attack Frequency Domain Attack Success Rate Effective Backdoor Attack