Adversarial DEfense

Adversarial defense in machine learning aims to create models robust against adversarial attacks—maliciously crafted inputs designed to cause misclassification. Current research focuses on developing both training-based defenses, such as adversarial training and techniques leveraging optimal transport or energy-based models, and test-time defenses, including input preprocessing and model reprogramming. These efforts are crucial for ensuring the reliability and security of machine learning systems across diverse applications, from image classification and natural language processing to structural health monitoring and malware detection, where vulnerabilities could have significant consequences.

Papers

October 30, 2024

CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense
Mingkun Zhang, Keping Bi, Wei Chen, Quanrun Chen, Jiafeng Guo, Xueqi Cheng
Diffusion Model Adversarial Example Adversarial DEfense Causal Variable

October 11, 2024

The Good, the Bad and the Ugly: Watermarks, Transferable Attacks and Adversarial Defenses
Grzegorz Głuch, Berkant Turan, Sai Ganesh Nagarajan, Sebastian Pokutta
Adversarial DEfense Transferable Attack Backdoor Watermark

October 6, 2024

Robustness Reprogramming for Representation Learning
Zhichao Hou, MohamadAli Torkamani, Hamid Krim, Xiaorui Liu
Deep Learning Native Robustness Representation Learning Adversarial DEfense Well Trained

September 5, 2024

Bypassing DARCY Defense: Indistinguishable Universal Adversarial Triggers
Zuquan Peng, Yuanyuan He, Jianbing Ni, Ben Niu
Adversarial Example Text Generation Adversarial DEfense Adversarial Trigger

August 28, 2024

Certified Causal Defense with Generalizable Robustness
Yiran Qiao, Yu Yin, Chen Chen, Jing Ma
Adversarial Attack Adversarial Perturbation Adversarial DEfense Certified Defense Causal Influence

August 27, 2024

August 21, 2024

Improving Out-of-Distribution Data Handling and Corruption Resistance via Modern Hopfield Networks
Saleh Sargolzaei, Luis Rueda
Computer Vision Model Adversarial DEfense MNIST Dataset Corruption Robustness Distribution Identification

August 20, 2024

Robust Image Classification: Defensive Strategies against FGSM and PGD Adversarial Attacks
Hetvi Waghela, Jaydip Sen, Sneha Rakshit
Adversarial Attack Adversarial Training Image Classification Adversarial Perturbation Adversarial DEfense Defense Strategy Fast Gradient Sign Method Projected Gradient Descent Attack

August 1, 2024

OTAD: An Optimal Transport-Induced Robust Model for Agnostic Adversarial Attack
Kuo Gai, Sicong Wang, Shihua Zhang
Adversarial Training Adversarial Perturbation Optimal Transport Adversarial DEfense Lipschitz Network Optimal Transport Map Agnostic Adversarial

July 8, 2024

Shedding More Light on Robust Classifiers under the lens of Energy-based Models
Mujtaba Hussain Mirza, Maria Rosaria Briglia, Senad Beadini, Iacopo Masi
Generative Adversarial Network Adversarial Training Camera Lens Energy Based Model Adversarial DEfense Adversarial Image Robust Classifier

June 24, 2024

UNICAD: A Unified Approach for Attack Detection, Noise Reduction and Novel Class Identification
Alvaro Lopez Pellicer, Kittipos Giatgong, Yi Li, Neeraj Suri, Plamen Angelov
Adversarial Attack Unified Framework Adversarial DEfense Unseen Class Novel Class Discovery Adversarial Scenario Noise Reduction Attack Detection

June 21, 2024

Deciphering the Definition of Adversarial Robustness for post-hoc OOD Detectors
Peter Lorenz, Mario Fernandez, Jens Müller, Ullrich Köthe
Adversarial Example Adversarial Robustness Distribution Detection Adversarial DEfense Definition Defining Redefinition Post Hoc Out of Distribution

June 20, 2024

Enhancing robustness of data-driven SHM models: adversarial training with circle loss
Xiangli Yang, Xijie Deng, Hanwei Zhang, Yang Zou, Jianxi Yang
Native Robustness Adversarial Example Adversarial Training Model Robustness Adversarial DEfense Structural Health Monitoring

June 16, 2024

Improving Adversarial Robustness via Decoupled Visual Representation Masking
Decheng Liu, Tao Chen, Chunlei Peng, Nannan Wang, Ruimin Hu, Xinbo Gao
Adversarial Robustness Adversarial DEfense Adversarial Noise Feature Masking

June 3, 2024

Assessing the Adversarial Security of Perceptual Hashing Algorithms
Jordan Madden, Moxanki Bhavsar, Lhamo Dorje, Xiaohua Li
Adversarial Attack Adversarial DEfense Inversion Attack Image Attack Perceptual Hashing

May 24, 2024

May 18, 2024

Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses
Thanh Nguyen, Tung M. Luu, Tri Ton, Chang D. Yoo
Adversarial Attack Offline Reinforcement Learning Robust Policy Adversarial DEfense

May 16, 2024

Adversarial Robustness for Visual Grounding of Multimodal Large Language Models
Kuofeng Gao, Yang Bai, Jiawang Bai, Yong Yang, Shu-Tao Xia
Adversarial Attack Adversarial Robustness Multimodal Large Language Model Visual Grounding Adversarial DEfense

Adversarial DEfense

Papers

CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense

The Good, the Bad and the Ugly: Watermarks, Transferable Attacks and Adversarial Defenses

Robustness Reprogramming for Representation Learning

Bypassing DARCY Defense: Indistinguishable Universal Adversarial Triggers

Certified Causal Defense with Generalizable Robustness

Adversarial Attacks and Defenses in Multivariate Time-Series Forecasting for Smart and Connected Infrastructures

TART: Boosting Clean Accuracy Through Tangent Direction Guided Adversarial Training

Improving Out-of-Distribution Data Handling and Corruption Resistance via Modern Hopfield Networks

Robust Image Classification: Defensive Strategies against FGSM and PGD Adversarial Attacks

OTAD: An Optimal Transport-Induced Robust Model for Agnostic Adversarial Attack

Shedding More Light on Robust Classifiers under the lens of Energy-based Models

UNICAD: A Unified Approach for Attack Detection, Noise Reduction and Novel Class Identification

Deciphering the Definition of Adversarial Robustness for post-hoc OOD Detectors

Enhancing robustness of data-driven SHM models: adversarial training with circle loss

Improving Adversarial Robustness via Decoupled Visual Representation Masking

Assessing the Adversarial Security of Perceptual Hashing Algorithms

Robust width: A lightweight and certifiable adversarial defense

Large Language Model Sentinel: LLM Agent for Adversarial Purification

Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses

Adversarial Robustness for Visual Grounding of Multimodal Large Language Models