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

July 21, 2022

July 19, 2022

Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms
Linbo Liu, Youngsuk Park, Trong Nghia Hoang, Hilaf Hasson, Jun Huan
Adversarial Attack Adversarial Example Multivariate Time Series Forecasting Defense Algorithm DEfense Mechanism

July 18, 2022

July 17, 2022

DIMBA: Discretely Masked Black-Box Attack in Single Object Tracking
Xiangyu Yin, Wenjie Ruan, Jonathan Fieldsend
Adversarial Attack Adversarial Example Visual Object Tracking Black Box Attack Tracking Method

July 16, 2022

Towards the Desirable Decision Boundary by Moderate-Margin Adversarial Training
Xiaoyu Liang, Yaguan Qian, Jianchang Huang, Xiang Ling, Bin Wang, Chunming Wu, Wassim Swaileh
Adversarial Attack Adversarial Example Adversarial Training Decision Boundary

July 14, 2022

Audio-guided Album Cover Art Generation with Genetic Algorithms
James Marien, Sam Leroux, Bart Dhoedt, Cedric De Boom
Adversarial Example Genetic Algorithm Novel Deep Learning Framework Album Cover

July 12, 2022

July 11, 2022

Statistical Detection of Adversarial examples in Blockchain-based Federated Forest In-vehicle Network Intrusion Detection Systems
Ibrahim Aliyu, Selinde van Engelenburg, Muhammed Bashir Muazu, Jinsul Kim, Chang Gyoon Lim
Adversarial Example Internet of Vehicle Vehicle Network Detection Rule

July 9, 2022

July 5, 2022

Query-Efficient Adversarial Attack Based on Latin Hypercube Sampling
Dan Wang, Jiayu Lin, Yuan-Gen Wang
Adversarial Attack Adversarial Example Attack Success Rate Boundary Attack

July 4, 2022

Adversarial Example

Papers

Careful What You Wish For: on the Extraction of Adversarially Trained Models

Rethinking Textual Adversarial Defense for Pre-trained Language Models

Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms

Multi-step domain adaptation by adversarial attack to $\mathcal{H} \Delta \mathcal{H}$-divergence

Easy Batch Normalization

Prior-Guided Adversarial Initialization for Fast Adversarial Training

DIMBA: Discretely Masked Black-Box Attack in Single Object Tracking

Towards the Desirable Decision Boundary by Moderate-Margin Adversarial Training

Audio-guided Album Cover Art Generation with Genetic Algorithms

Practical Attacks on Machine Learning: A Case Study on Adversarial Windows Malware

Exploring Adversarial Examples and Adversarial Robustness of Convolutional Neural Networks by Mutual Information

Adversarial Robustness Assessment of NeuroEvolution Approaches

Frequency Domain Model Augmentation for Adversarial Attack

Statistical Detection of Adversarial examples in Blockchain-based Federated Forest In-vehicle Network Intrusion Detection Systems

Dynamic Time Warping based Adversarial Framework for Time-Series Domain

Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Features

Jacobian Norm with Selective Input Gradient Regularization for Improved and Interpretable Adversarial Defense

Query-Efficient Adversarial Attack Based on Latin Hypercube Sampling

Wild Networks: Exposure of 5G Network Infrastructures to Adversarial Examples

Hessian-Free Second-Order Adversarial Examples for Adversarial Learning