Adaptive Adversarial Attack

Adaptive adversarial attacks aim to circumvent security measures in machine learning models by dynamically adjusting attack strategies based on the deployed defenses. Current research focuses on developing robust detection methods, often employing adversarial retraining or recurrent feedback mechanisms to improve model resilience, and creating more effective attacks that target specific vulnerabilities, such as localized regions in images or 3D point clouds. This field is crucial for enhancing the security and reliability of machine learning systems across various applications, from image recognition and object detection to speaker verification and augmented reality, by understanding and mitigating the threat of sophisticated, adaptive attacks.

Papers

December 26, 2024

Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks
Yu Qiao, Apurba Adhikary, Kitae Kim, Eui-Nam Huh, Zhu Han, Choong Seon Hong
Adversarial Attack Adversarial Training Edge Network Adversarial Distillation Federated Training Adaptive Adversarial Attack

April 18, 2024

Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectors
Raz Lapid, Almog Dubin, Moshe Sipper
Adversarial Detection Treasure Trove Adversarial Retraining Adaptive Adversarial Attack

March 31, 2024

Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches
Lingxuan Wu, Xiao Yang, Yinpeng Dong, Liuwei Xie, Hang Su, Jun Zhu
Adversarial Attack Adversarial Patch Active Perception Iterative Feedback Active Defense Adaptive Adversarial Attack

January 18, 2024

Artwork Protection Against Neural Style Transfer Using Locally Adaptive Adversarial Color Attack
Zhongliang Guo, Junhao Dong, Yifei Qian, Kaixuan Wang, Weiye Li, Ziheng Guo, Yuheng Wang, Yanli Li, Ognjen Arandjelović, Lei Fang
Neural Style Transfer Image Protection Adversarial Color Adaptive Adversarial Attack

December 12, 2023

Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training
Qian Li, Yuxiao Hu, Yinpeng Dong, Dongxiao Zhang, Yuntian Chen
Adversarial Example Adversarial Training Human Driving Focus Threat Word Adversarial Training Algorithm Standard Adversarial Training Adaptive Adversarial Attack

March 12, 2023

Adaptive Local Adversarial Attacks on 3D Point Clouds for Augmented Reality
Weiquan Liu, Shijun Zheng, Cheng Wang
Adversarial Example 3D Point Cloud Augmented Reality Gradient Attack Adversarial Point Cloud 3D Adversarial Adaptive Adversarial Attack

March 5, 2023

Consistent Valid Physically-Realizable Adversarial Attack against Crowd-flow Prediction Models
Hassan Ali, Muhammad Atif Butt, Fethi Filali, Ala Al-Fuqaha, Junaid Qadir
Adversarial Attack Adversarial Perturbation Adversarial Vulnerability Flow Prediction Crowd Flow Adaptive Adversarial Attack

March 3, 2022

Ad2Attack: Adaptive Adversarial Attack on Real-Time UAV Tracking
Changhong Fu, Sihang Li, Xinnan Yuan, Junjie Ye, Ziang Cao, Fangqiang Ding
Unmanned Aerial Vehicle Tracking Adaptive Adversarial Attack

February 11, 2022

On the Detection of Adaptive Adversarial Attacks in Speaker Verification Systems
Zesheng Chen
Adversarial Attack Data Detection Speaker Verification Real World Attack Adaptive Adversarial Attack

Adaptive Adversarial Attack

Papers

Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks

Fortify the Guardian, Not the Treasure: Resilient Adversarial Detectors

Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches

Artwork Protection Against Neural Style Transfer Using Locally Adaptive Adversarial Color Attack

Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training

Adaptive Local Adversarial Attacks on 3D Point Clouds for Augmented Reality

Consistent Valid Physically-Realizable Adversarial Attack against Crowd-flow Prediction Models

Ad2Attack: Adaptive Adversarial Attack on Real-Time UAV Tracking

On the Detection of Adaptive Adversarial Attacks in Speaker Verification Systems