Multi Step Attack

Multi-step attacks represent a sophisticated class of adversarial attacks that iteratively perturb inputs to compromise machine learning models, exceeding the capabilities of simpler, single-step attacks. Current research focuses on understanding and mitigating these attacks across various domains, including image classification, natural language processing, and network security, employing techniques like gradient-based optimization and graph neural networks to model attack strategies and develop defenses. The ability to design robust defenses against multi-step attacks is crucial for ensuring the reliability and security of machine learning systems in diverse real-world applications, ranging from cybersecurity to the integrity of online social networks.

Papers

October 14, 2024

Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered Clues
Qibing Ren, Hao Li, Dongrui Liu, Zhanxu Xie, Xiaoya Lu, Yu Qiao, Lei Sha, Junchi Yan, Lizhuang Ma, Jing Shao
Jailbreak Attack Attack Method Superficial Clue Step Attack Multi Step Attack

October 2, 2024

On Using Certified Training towards Empirical Robustness
Alessandro De Palma, Serge Durand, Zakaria Chihani, François Terrier, Caterina Urban
Adversarial Attack Training Data Adversarial Example Adversarial Training Step Attack Multi Step Attack

June 14, 2024

Semantic Membership Inference Attack against Large Language Models
Hamid Mozaffari, Virendra J. Marathe
Membership Inference Attack Semantic Content Multi Step Attack

April 28, 2024

Multi-stage Attack Detection and Prediction Using Graph Neural Networks: An IoT Feasibility Study
Hamdi Friji, Ioannis Mavromatis, Adrian Sanchez-Mompo, Pietro Carnelli, Alexis Olivereau, Aftab Khan
Graph Neural Network Human Prediction Intrusion Detection System Feasibility Study Cyber Threat Multi Step Attack

March 19, 2024

Electioneering the Network: Dynamic Multi-Step Adversarial Attacks for Community Canvassing
Saurabh Sharma, Ambuj SIngh
Network Programming Adversarial Text Gradient Based Attack Multi Step Adversarial Attack Adversarial Data Collection Multi Step Attack Medium Manipulation

December 3, 2023

Rethinking PGD Attack: Is Sign Function Necessary?
Junjie Yang, Tianlong Chen, Xuxi Chen, Zhangyang Wang, Yingbin Liang
Adversarial Attack Gradient Descent Adversarial Input Multi Step Attack Projected Gradient Descent Attack Sign Function

June 2, 2023

Hyperparameter Learning under Data Poisoning: Analysis of the Influence of Regularization via Multiobjective Bilevel Optimization
Javier Carnerero-Cano, Luis Muñoz-González, Phillippa Spencer, Emil C. Lupu
Native Robustness General Analysis Bilevel Optimization Data Poisoning Multi Step Attack Optimal Attack

May 18, 2023

Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning
Yinglun Xu, Gagandeep Singh
Unknown Dynamic Attack Efficacy Multi Step Attack Reward Poisoning Attack

June 6, 2022

Fast Adversarial Training with Adaptive Step Size
Zhichao Huang, Yanbo Fan, Chen Liu, Weizhong Zhang, Yong Zhang, Mathieu Salzmann, Sabine Süsstrunk, Jue Wang
Adversarial Attack Adversarial Training Step Size Fast Adversarial Training Catastrophic Overfitting Step Attack Multi Step Attack

May 30, 2022

Why Adversarial Training of ReLU Networks Is Difficult?
Xu Cheng, Hao Zhang, Yue Xin, Wen Shen, Jie Ren, Quanshi Zhang
Adversarial Training Adversarial Perturbation Hessian Matrix Gradient Norm ReLU Network Multi Step Attack

February 27, 2022

The Art of Manipulation: Threat of Multi-Step Manipulative Attacks in Security Games
Thanh H. Nguyen, Arunesh Sinha
Strategic Manipulation Art Specific Information Threat Word Step Attack Security Game Multi Step Attack Stackelberg Security Game