Adversarial Framework

Adversarial frameworks are a class of machine learning techniques that leverage competition between two or more models to improve robustness, interpretability, or other desirable properties. Current research focuses on applying these frameworks to diverse areas, including improving the robustness of deep neural networks (DNNs) against adversarial attacks, enhancing the security of large language models (LLMs), and developing more reliable anomaly detection methods. These techniques are significant because they address critical vulnerabilities in existing machine learning systems, leading to more reliable and trustworthy AI applications across various domains.

Papers

October 11, 2024

AdvDiffuser: Generating Adversarial Safety-Critical Driving Scenarios via Guided Diffusion
Yuting Xie, Xianda Guo, Cong Wang, Kunhua Liu, Long Chen
Adversarial Attack Autonomous Driving Multi Scenario Adversarial Text Adversarial Framework Guided Diffusion Safety Critical Scenario

October 1, 2024

Deep Adversarial Learning with Activity-Based User Discrimination Task for Human Activity Recognition
Francisco M. Calatrava-Nicolás, Oscar Martinez Mozos
Activity Recognition Generative Adversarial Adversarial Framework Discriminative Task

August 21, 2024

A Joint Noise Disentanglement and Adversarial Training Framework for Robust Speaker Verification
Xujiang Xing, Mingxing Xu, Thomas Fang Zheng
Speaker Verification Speech Encoder Adversarial Framework Ecapa TDNN Robust Speaker Verification

August 20, 2024

Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models
Hongbang Yuan, Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao
Unlearning Framework Adversarial Framework Unlearned Model Robust Unlearning Adversarial Unlearning

August 17, 2024

Attack Anything: Blind DNNs via Universal Background Adversarial Attack
Jiawei Lian, Shaohui Mei, Xiaofei Wang, Yi Wang, Lefan Wang, Yingjie Lu, Mingyang Ma, Lap-Pui Chau
Adversarial Attack Adversarial Perturbation Cyber Attack Attack Strategy Adversarial Framework Universal Adversarial

June 6, 2024

Batch-in-Batch: a new adversarial training framework for initial perturbation and sample selection
Yinting Wu, Pai Peng, Bo Cai, Le Li, .
Adversarial Training Adversarial Sample Adversarial Framework Large Batch Adversarial Evaluation Adversarial Setting Sample Selection

May 31, 2024

Investigating and unmasking feature-level vulnerabilities of CNNs to adversarial perturbations
Davide Coppola, Hwee Kuan Lee
Adversarial Perturbation CNN Model Adversarial Framework Attack Surface

May 25, 2024

R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model
Changhoon Kim, Kyle Min, Yezhou Yang
Text to Image Diffusion Model Text to Image Adversarial Framework Textual Adversarial Attack Adversarial Challenge

April 29, 2024

Why You Should Not Trust Interpretations in Machine Learning: Adversarial Attacks on Partial Dependence Plots
Xi Xin, Giles Hooker, Fei Huang
Machine Learning Adversarial Attack Black Box Model Model Interpretability Adversarial Framework Partial Dependence Plot Dependence Shift

April 24, 2024

A General Black-box Adversarial Attack on Graph-based Fake News Detectors
Peican Zhu, Zechen Pan, Yang Liu, Jiwei Tian, Keke Tang, Zhen Wang
Graph Neural Network Fake News Adversarial Framework Black Box Adversarial Attack Traditional Adversarial Fake User

February 29, 2024

Utilizing Local Hierarchy with Adversarial Training for Hierarchical Text Classification
Zihan Wang, Peiyi Wang, Houfeng Wang
Adversarial Training Ground Truth Multi Label Classification Part Whole Hierarchy Adversarial Framework Taxonomic Classification Hierarchical Text Classification

January 24, 2024

Boosting the Transferability of Adversarial Examples via Local Mixup and Adaptive Step Size
Junlin Liu, Xinchen Lyu
Adversarial Example Task Transferability Adversarial Image Step Size Adversarial Framework Adversarial Generation Local Mixup

December 15, 2023

Embodied Adversarial Attack: A Dynamic Robust Physical Attack in Autonomous Driving
Yitong Sun, Yao Huang, Xingxing Wei
Adversarial Attack Autonomous Driving Adversarial Example Adversarial Framework

October 25, 2023

Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks
Aradhana Sinha, Ananth Balashankar, Ahmad Beirami, Thi Avrahami, Jilin Chen, Alex Beutel
Adversarial Example Human in the Loop Adversarial Framework

October 2, 2023

Large Language Model-Powered Smart Contract Vulnerability Detection: New Perspectives
Sihao Hu, Tiansheng Huang, Fatih İlhan, Selim Furkan Tekin, Ling Liu
Large Language Security Vulnerability New Perspective Smart Contract Adversarial Framework

September 3, 2023

Enhancing Infrared Small Target Detection Robustness with Bi-Level Adversarial Framework
Zhu Liu, Zihang Chen, Jinyuan Liu, Long Ma, Xin Fan, Risheng Liu
Adversarial Attack Infrared Small Target Detection Adversarial Framework Target Detection Infrared Small Robustness Enhancement

July 19, 2023

July 14, 2023

Alleviating the Effect of Data Imbalance on Adversarial Training
Guanlin Li, Guowen Xu, Tianwei Zhang
Adversarial Example Adversarial Training Mixed Effect Data Imbalance Adversarial Framework

March 25, 2023

CFA: Class-wise Calibrated Fair Adversarial Training
Zeming Wei, Yifei Wang, Yiwen Guo, Yisen Wang
Adversarial Example Adversarial Training Adversarial Robustness Adversarial Framework Adversarial Setting Fair Adversarial

Adversarial Framework

Papers

AdvDiffuser: Generating Adversarial Safety-Critical Driving Scenarios via Guided Diffusion

Deep Adversarial Learning with Activity-Based User Discrimination Task for Human Activity Recognition

A Joint Noise Disentanglement and Adversarial Training Framework for Robust Speaker Verification

Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models

Attack Anything: Blind DNNs via Universal Background Adversarial Attack

Batch-in-Batch: a new adversarial training framework for initial perturbation and sample selection

Investigating and unmasking feature-level vulnerabilities of CNNs to adversarial perturbations

R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model

Why You Should Not Trust Interpretations in Machine Learning: Adversarial Attacks on Partial Dependence Plots

A General Black-box Adversarial Attack on Graph-based Fake News Detectors

Utilizing Local Hierarchy with Adversarial Training for Hierarchical Text Classification

Boosting the Transferability of Adversarial Examples via Local Mixup and Adaptive Step Size

Embodied Adversarial Attack: A Dynamic Robust Physical Attack in Autonomous Driving

Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks

Large Language Model-Powered Smart Contract Vulnerability Detection: New Perspectives

Enhancing Infrared Small Target Detection Robustness with Bi-Level Adversarial Framework

Adversarial Likelihood Estimation With One-Way Flows

Towards Building More Robust Models with Frequency Bias

Alleviating the Effect of Data Imbalance on Adversarial Training

CFA: Class-wise Calibrated Fair Adversarial Training