General Adversarial

General adversarial research focuses on improving the robustness of machine learning models against adversarial attacks, which involve subtly altering inputs to cause misclassification. Current research emphasizes developing more efficient adversarial training methods, such as those leveraging intrinsic dimensionality or dynamic perturbations, and exploring novel attack strategies tailored to specific domains like medical imaging, graph data, and network security. This work is crucial for enhancing the reliability and security of AI systems across various applications, particularly in safety-critical contexts where model vulnerability poses significant risks.

Papers

September 10, 2024

Unrevealed Threats: A Comprehensive Study of the Adversarial Robustness of Underwater Image Enhancement Models
Siyu Zhai, Zhibo He, Xiaofeng Cong, Junming Hou, Jie Gui, Jian Wei You, Xin Gong, James Tin-Yau Kwok, Yuan Yan Tang
Adversarial Attack Adversarial Robustness Underwater Image Comprehensive Study Underwater Image Enhancement General Adversarial New Threat

May 27, 2024

Exploiting the Layered Intrinsic Dimensionality of Deep Models for Practical Adversarial Training
Enes Altinisik, Safa Messaoud, Husrev Taha Sencar, Hassan Sajjad, Sanjay Chawla
Adversarial Example Adversarial Training Deep Model Better Robustness Intrinsic Dimensionality General Adversarial Manifold Adversarial

March 11, 2024

Dynamic Perturbation-Adaptive Adversarial Training on Medical Image Classification
Shuai Li, Xiaoguang Ma, Shancheng Jiang, Lu Meng
Adversarial Example Adversarial Training Medical Image Classification General Adversarial

November 27, 2023

Attend Who is Weak: Enhancing Graph Condensation via Cross-Free Adversarial Training
Xinglin Li, Kun Wang, Hanhui Deng, Yuxuan Liang, Di Wu
Training Graph Synthetic Graph Adversarial Risk Graph Condensation General Adversarial Adversarial Clothes

October 31, 2023

Amoeba: Circumventing ML-supported Network Censorship via Adversarial Reinforcement Learning
Haoyu Liu, Alec F. Diallo, Paul Patras
Adversarial Reinforcement Learning General Adversarial New Censorship Instance Global Bypass Consistency Flow Generative Adversarial Network

March 25, 2023

AdvCheck: Characterizing Adversarial Examples via Local Gradient Checking
Ruoxi Chen, Haibo Jin, Jinyin Chen, Haibin Zheng
Deep Neural Network Adversarial Example Detection Model Local Gradient General Adversarial

March 3, 2023

Multi-Agent Adversarial Training Using Diffusion Learning
Ying Cao, Elsa Rizk, Stefan Vlaski, Ali H. Sayed
Adversarial Attack Multi Agent Adversarial Learning Convex Optimization Diffusion Learning General Adversarial

February 17, 2023

Adversarial Contrastive Distillation with Adaptive Denoising
Yuzheng Wang, Zhaoyu Chen, Dingkang Yang, Yang Liu, Siao Liu, Wenqiang Zhang, Lizhe Qi
Contrastive Distillation General Adversarial Adversarial Robustness Distillation Parameter Aware Robustness

October 27, 2022

TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack
Yu Cao, Dianqi Li, Meng Fang, Tianyi Zhou, Jun Gao, Yibing Zhan, Dacheng Tao
Question Answering Model Answer Prediction General Adversarial Sentence Level Attack Adversarial Context

June 27, 2022

On the Complexity of Adversarial Decision Making
Dylan J. Foster, Alexander Rakhlin, Ayush Sekhari, Karthik Sridharan
Adversarial Attack Complexity Matter Adversarial Markov Decision Process Adversarial Reward General Adversarial

April 11, 2022

Generalizing Adversarial Explanations with Grad-CAM
Tanmay Chakraborty, Utkarsh Trehan, Khawla Mallat, Jean-Luc Dugelay
Black Box Grad CAM Class Activation Mapping General Adversarial

February 15, 2022

Random Walks for Adversarial Meshes
Amir Belder, Gal Yefet, Ran Ben Izhak, Ayellet Tal
Adversarial Attack Random Walk General Adversarial Mesh Attack

December 6, 2021

Adversarial Machine Learning In Network Intrusion Detection Domain: A Systematic Review
Huda Ali Alatwi, Charles Morisset
Deep Learning Model Adversarial Example Adversarial Learning Systematic Review Network Intrusion General Adversarial