Adversarial Instance

Adversarial instances are subtly modified inputs designed to fool machine learning models, primarily deep neural networks (DNNs), into making incorrect predictions. Current research focuses on generating these instances using evolutionary algorithms and adversarial training techniques, analyzing their impact on model robustness and fairness across various architectures including recurrent and diffusion models, and developing methods to detect and mitigate their effects. Understanding and addressing adversarial instances is crucial for improving the reliability and trustworthiness of AI systems in safety-critical applications and advancing the broader field of machine learning.

Papers

June 24, 2024

Evaluating the Robustness of Deep-Learning Algorithm-Selection Models by Evolving Adversarial Instances
Emma Hart, Quentin Renau, Kevin Sim, Mohamad Alissa
Deep Neural Network Native Robustness Adversarial Sample Algorithm Selection Deep Recurrent Neural Network Adversarial Instance

May 1, 2024

ASAM: Boosting Segment Anything Model with Adversarial Tuning
Bo Li, Haoke Xiao, Lv Tang
Segment Anything Model Segmentation Task Sharpness Aware Minimization Adversarial Fine Tuning Adversarial Instance

April 1, 2024

The Double-Edged Sword of Input Perturbations to Robust Accurate Fairness
Xuran Li, Peng Wu, Yanting Chen, Xingjun Ma, Zhen Zhang, Kaixiang Dong
Adversarial Perturbation Input Perturbation Adversarial Instance Robust Fairness Adversarial Bias

January 12, 2024

Adversarial Examples are Misaligned in Diffusion Model Manifolds
Peter Lorenz, Ricard Durall, Janis Keuper
Diffusion Model Adversarial Attack Adversarial Example Adversarial Robustness Adversarial Instance Manifold Diffusion

November 14, 2023

Towards Improving Robustness Against Common Corruptions in Object Detectors Using Adversarial Contrastive Learning
Shashank Kotyan, Danilo Vasconcellos Vargas
Adversarial Attack Native Robustness Adversarial Perturbation Object Detector Common Corruption Adversarial Contrastive Learning Adversarial Instance

August 11, 2023

Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregation
Xuannan Liu, Yaoyao Zhong, Yuhang Zhang, Lixiong Qin, Weihong Deng
Aggregated Gradient Adversarial Instance Enhancing Generalization Gradient Aggregation

August 3, 2023

Hard Adversarial Example Mining for Improving Robust Fairness
Chenhao Lin, Xiang Ji, Yulong Yang, Qian Li, Chao Shen, Run Wang, Liming Fang
Adversarial Example Adversarial Training Adversarial Instance Robust Fairness

May 18, 2023

RobustFair: Adversarial Evaluation through Fairness Confusion Directed Gradient Search
Xuran Li, Peng Wu, Kaixiang Dong, Zhen Zhang, Yanting Chen
Native Robustness Adversarial Example Adversarial Perturbation Adversarial Evaluation Adversarial Instance Fairness Loss

March 13, 2023

Can Adversarial Examples Be Parsed to Reveal Victim Model Information?
Yuguang Yao, Jiancheng Liu, Yifan Gong, Xiaoming Liu, Yanzhi Wang, Xue Lin, Sijia Liu
Adversarial Attack Adversarial Example Transferable Attack Adversarial Instance Victim Model

December 13, 2022

AdvMIL: Adversarial Multiple Instance Learning for the Survival Analysis on Whole-Slide Images
Pei Liu, Luping Ji, Feng Ye, Bo Fu
Computational Pathology Whole Slide Image Adversarial Instance Whole Slide Survival Distribution Survival Analysis Method

August 29, 2022

Reducing Certified Regression to Certified Classification for General Poisoning Attacks
Zayd Hammoudeh, Daniel Lowd
Native Robustness Novel Regression Poisoning Attack Model Robustness Adversarial Instance Stochastic Defense

August 17, 2022

An Evolutionary, Gradient-Free, Query-Efficient, Black-Box Algorithm for Generating Adversarial Instances in Deep Networks
Raz Lapid, Zvika Haramaty, Moshe Sipper
Adversarial Example Deep Network Black Box Adversarial Data QuEry Based Attack Adversarial Instance

June 2, 2022

FACM: Intermediate Layer Still Retain Effective Features against Adversarial Examples
Xiangyuan Yang, Jie Lin, Hanlin Zhang, Xinyu Yang, Peng Zhao
Adversarial Attack Adversarial Example Intermediate Layer Predictive Distribution Adversarial Instance Effective Feature

May 20, 2022

Exploring the Trade-off between Plausibility, Change Intensity and Adversarial Power in Counterfactual Explanations using Multi-objective Optimization
Javier Del Ser, Alejandro Barredo-Arrieta, Natalia Díaz-Rodríguez, Francisco Herrera, Andreas Holzinger
Counterfactual Explanation Multi Objective Optimization Counterfactual Generation Counterfactual Example Explanation Plausibility Adversarial Instance Adversarial Capability

May 2, 2022

MIRST-DM: Multi-Instance RST with Drop-Max Layer for Robust Classification of Breast Cancer
Shoukun Sun, Min Xian, Aleksandar Vakanski, Hossny Ghanem
Adversarial Robustness Breast Cancer Robust Classification Adversarial Instance Dropout Layer Robust Self

January 25, 2022

Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation
Zayd Hammoudeh, Daniel Lowd
Target Amazon Ally Adversarial Instance Influence Estimation Training Set Attack

December 14, 2021

On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training
Chen Liu, Zhichao Huang, Mathieu Salzmann, Tong Zhang, Sabine Süsstrunk
Adversarial Attack Adversarial Training Global Impact Adversarial Learning Generalization Performance Adversarial Instance

November 13, 2021

Measuring the Contribution of Multiple Model Representations in Detecting Adversarial Instances
Daniel Steinberg, Paul Munro
Adversarial Attack Deep Learning Model Adversarial Example Client Contribution Multiple Model Adversarial Instance

Adversarial Instance

Papers

Evaluating the Robustness of Deep-Learning Algorithm-Selection Models by Evolving Adversarial Instances

ASAM: Boosting Segment Anything Model with Adversarial Tuning

The Double-Edged Sword of Input Perturbations to Robust Accurate Fairness

Adversarial Examples are Misaligned in Diffusion Model Manifolds

Towards Improving Robustness Against Common Corruptions in Object Detectors Using Adversarial Contrastive Learning

Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregation

Hard Adversarial Example Mining for Improving Robust Fairness

RobustFair: Adversarial Evaluation through Fairness Confusion Directed Gradient Search

Can Adversarial Examples Be Parsed to Reveal Victim Model Information?

AdvMIL: Adversarial Multiple Instance Learning for the Survival Analysis on Whole-Slide Images

Reducing Certified Regression to Certified Classification for General Poisoning Attacks

An Evolutionary, Gradient-Free, Query-Efficient, Black-Box Algorithm for Generating Adversarial Instances in Deep Networks

FACM: Intermediate Layer Still Retain Effective Features against Adversarial Examples

Exploring the Trade-off between Plausibility, Change Intensity and Adversarial Power in Counterfactual Explanations using Multi-objective Optimization

MIRST-DM: Multi-Instance RST with Drop-Max Layer for Robust Classification of Breast Cancer

Identifying a Training-Set Attack's Target Using Renormalized Influence Estimation

On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training

Measuring the Contribution of Multiple Model Representations in Detecting Adversarial Instances