Label Attack

Label attacks target machine learning models by manipulating their input data or training process to cause misclassifications or reveal sensitive information about the training data. Current research focuses on developing increasingly effective attacks, particularly in scenarios with limited access to model internals (black-box attacks) or only label information, employing techniques like adversarial perturbations, data poisoning, and similarity-based inference. These attacks highlight vulnerabilities in various model architectures, from image classifiers and vision-language models to graph neural networks, underscoring the critical need for robust defenses to ensure the security and privacy of machine learning systems in real-world applications.

Papers

May 27, 2024

OSLO: One-Shot Label-Only Membership Inference Attacks
Yuefeng Peng, Jaechul Roh, Subhransu Maji, Amir Houmansadr
Adversarial Attack Adversarial Perturbation Membership Inference Attack Cyber Attack Label Attack

March 18, 2024

Impart: An Imperceptible and Effective Label-Specific Backdoor Attack
Jingke Zhao, Zan Wang, Yongwei Wang, Lanjun Wang
Backdoor Attack Attack Success Rate Clean Label Backdoor Attack Imperceptible Pattern Label Attack

February 5, 2024

Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
Yuancheng Xu, Jiarui Yao, Manli Shu, Yanchao Sun, Zichu Wu, Ning Yu, Tom Goldstein, Furong Huang
Vision Language Model Label Attack Persuasion Mode

November 26, 2023

Confidence Is All You Need for MI Attacks
Abhishek Sinha, Himanshi Tibrewal, Mansi Gupta, Nikhar Waghela, Shivank Garg
Training Data Machine Learning Model Membership Inference Attack Sensitive Data High Confidence Label Attack MI Attack

October 5, 2023

Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning
Harsh Chaudhari, Giorgio Severi, Alina Oprea, Jonathan Ullman
Membership Inference Attack Membership Inference Pace Adaptive Membership Privacy Label Attack Poisoning Efficiency Label Only Membership Inference Attack

May 4, 2023

Single Node Injection Label Specificity Attack on Graph Neural Networks via Reinforcement Learning
Dayuan Chen, Jian Zhang, Yuqian Lv, Jinhuan Wang, Hongjie Ni, Shanqing Yu, Zhen Wang, Qi Xuan
Reinforcement Learning Graph Neural Network Gradient Based Adversarial Node Injection Label Attack Graph Injection Attack

November 16, 2022

Attacking Object Detector Using A Universal Targeted Label-Switch Patch
Avishag Shapira, Ron Bitton, Dan Avraham, Alon Zolfi, Yuval Elovici, Asaf Shabtai
Adversarial Attack Object Detector Adversarial Patch Universal Image Deep Learning Based Object Label Shift Adversarial Pattern Label Attack

November 1, 2022

Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks
Jianan Zhou, Jianing Zhu, Jingfeng Zhang, Tongliang Liu, Gang Niu, Bo Han, Masashi Sugiyama
Adversarial Example Adversarial Training Complementary Benefit Complementary Label Label Attack Adversarial Optimization

October 21, 2022

TCAB: A Large-Scale Text Classification Attack Benchmark
Kalyani Asthana, Zhouhang Xie, Wencong You, Adam Noack, Jonathan Brophy, Sameer Singh, Daniel Lowd
Adversarial Attack Text Classification Text Attack Label Attack

September 16, 2022

A Systematic Evaluation of Node Embedding Robustness
Alexandru Mara, Jefrey Lijffijt, Stephan Günnemann, Tijl De Bie
Native Robustness Node Classification Poisoning Attack Label Attack

July 11, 2022

Towards Effective Multi-Label Recognition Attacks via Knowledge Graph Consistency
Hassan Mahmood, Ehsan Elhamifar
Adversarial Attack Multi Label Knowledge Alignment Label Attack Label Perturbation

May 29, 2022

Superclass Adversarial Attack
Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki
Adversarial Attack True Class Label Attack

March 10, 2022

Similarity-based Label Inference Attack against Training and Inference of Split Learning
Junlin Liu, Xinchen Lyu, Qimei Cui, Xiaofeng Tao
Training Data Differential Privacy Scientific Inference Split Learning Label Inference Attack Label Attack Private Label

March 2, 2022

Label Leakage and Protection from Forward Embedding in Vertical Federated Learning
Jiankai Sun, Xin Yang, Yuanshun Yao, Chong Wang
Differential Privacy Vertical Federated Learning PRIvacy Leakage Label Attack Private Label Label Leakage

January 20, 2022

TextHacker: Learning based Hybrid Local Search Algorithm for Text Hard-label Adversarial Attack
Zhen Yu, Xiaosen Wang, Wanxiang Che, Kun He
Adversarial Attack Local Search Textual Adversarial Attack Text Detector Label Attack Hard Label Attack