Adversarial Example

Adversarial examples are subtly altered inputs designed to fool machine learning models, primarily deep neural networks (DNNs), into making incorrect predictions. Current research focuses on improving model robustness against these attacks, exploring techniques like ensemble methods, multi-objective representation learning, and adversarial training, often applied to architectures such as ResNets and Vision Transformers. Understanding and mitigating the threat of adversarial examples is crucial for ensuring the reliability and security of AI systems across diverse applications, from image classification and natural language processing to malware detection and autonomous driving. The development of robust defenses and effective attack detection methods remains a significant area of ongoing investigation.

Papers

September 16, 2022

September 15, 2022

September 14, 2022

Robust Transferable Feature Extractors: Learning to Defend Pre-Trained Networks Against White Box Adversaries
Alexander Cann, Ian Colbert, Ihab Amer
Adversarial Example Adversarial Robustness Adversarial DEfense White Box Feature Transfer Pre Processing Zero Shot Adversarial Robustness

September 13, 2022

Adversarial Coreset Selection for Efficient Robust Training
Hadi M. Dolatabadi, Sarah Erfani, Christopher Leckie
Adversarial Attack Adversarial Example Adversarial Training Robust Training COreset Selection

September 11, 2022

Resisting Deep Learning Models Against Adversarial Attack Transferability via Feature Randomization
Ehsan Nowroozi, Mohammadreza Mohammadi, Pargol Golmohammadi, Yassine Mekdad, Mauro Conti, Selcuk Uluagac
Adversarial Attack Adversarial Example Adversarial Transferability Adversarial Manipulation

September 9, 2022

The Space of Adversarial Strategies
Ryan Sheatsley, Blaine Hoak, Eric Pauley, Patrick McDaniel
Adversarial Attack Adversarial Example Adversarial Learning Deep Space Attack Efficacy Ensemble Attack

September 7, 2022

September 6, 2022

Instance Attack:An Explanation-based Vulnerability Analysis Framework Against DNNs for Malware Detection
Sun RuiJin, Guo ShiZe, Guo JinHong, Xing ChangYou, Yang LuMing, Guo Xi, Pan ZhiSong
Deep Neural Network Adversarial Example Malware Detection Malware Classifier Vulnerability Analysis

September 5, 2022

August 31, 2022

August 30, 2022

Robustness and invariance properties of image classifiers
Apostolos Modas
Native Robustness Adversarial Example Adversarial Perturbation Deep Network Image Classifier Invariance Property State of the Art Robustness

August 28, 2022

Cross-domain Cross-architecture Black-box Attacks on Fine-tuned Models with Transferred Evolutionary Strategies
Yinghua Zhang, Yangqiu Song, Kun Bai, Qiang Yang
Adversarial Attack Adversarial Example New Attack Fine Tuned Model Adversarial Generation Transfer Evolutionary Optimization

August 27, 2022

August 24, 2022

Rethinking Cost-sensitive Classification in Deep Learning via Adversarial Data Augmentation
Qiyuan Chen, Raed Al Kontar, Maher Nouiehed, Jessie Yang, Corey Lester
Deep Learning Adversarial Example Cost Sensitive Adversarial Data Augmentation Price Sensitivity

Adversarial Example

Papers

A Large-scale Multiple-objective Method for Black-box Attack against Object Detection

Enhance the Visual Representation via Discrete Adversarial Training

Adversarially Robust Learning: A Generic Minimax Optimal Learner and Characterization

Improving Robust Fairness via Balance Adversarial Training

Robust Transferable Feature Extractors: Learning to Defend Pre-Trained Networks Against White Box Adversaries

Adversarial Coreset Selection for Efficient Robust Training

Resisting Deep Learning Models Against Adversarial Attack Transferability via Feature Randomization

The Space of Adversarial Strategies

Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examples

On the Transferability of Adversarial Examples between Encrypted Models

Instance Attack:An Explanation-based Vulnerability Analysis Framework Against DNNs for Malware Detection

Red Teaming with Mind Reading: White-Box Adversarial Policies Against RL Agents

Evaluating the Susceptibility of Pre-Trained Language Models via Handcrafted Adversarial Examples

Be Your Own Neighborhood: Detecting Adversarial Example by the Neighborhood Relations Built on Self-Supervised Learning

Unrestricted Adversarial Samples Based on Non-semantic Feature Clusters Substitution

Robustness and invariance properties of image classifiers

Cross-domain Cross-architecture Black-box Attacks on Fine-tuned Models with Transferred Evolutionary Strategies

SA: Sliding attack for synthetic speech detection with resistance to clipping and self-splicing

Adversarial Robustness for Tabular Data through Cost and Utility Awareness

Rethinking Cost-sensitive Classification in Deep Learning via Adversarial Data Augmentation