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

December 21, 2021

A Theoretical View of Linear Backpropagation and Its Convergence
Ziang Li, Yiwen Guo, Haodi Liu, Changshui Zhang
Adversarial Attack Adversarial Example Early Stage Convergence Back Propagation

December 20, 2021

Certified Federated Adversarial Training
Giulio Zizzo, Ambrish Rawat, Mathieu Sinn, Sergio Maffeis, Chris Hankin
Adversarial Example Adversarial Training Adversarial Robustness Federated Adversarial

December 17, 2021

Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations
Siddhant Arora, Danish Pruthi, Norman Sadeh, William W. Cohen, Zachary C. Lipton, Graham Neubig
Adversarial Example Human Understanding BERT Model Model Confidence Deception Detection Model Reconciling Explanation

December 16, 2021

DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models
Hongyu Zhu, Yan Chen, Jing Yan, Jing Liu, Yu Hong, Ying Chen, Hua Wu, Haifeng Wang
Native Robustness Adversarial Example Question Answering Robustness Evaluation Chinese Dataset Level Perturbation Question Template

December 15, 2021

On the Convergence and Robustness of Adversarial Training
Yisen Wang, Xingjun Ma, James Bailey, Jinfeng Yi, Bowen Zhou, Quanquan Gu
Native Robustness Adversarial Example Adversarial Training Early Stage Convergence Better Robustness Inner Optimization

December 14, 2021

December 13, 2021

December 12, 2021

Quantifying and Understanding Adversarial Examples in Discrete Input Spaces
Volodymyr Kuleshov, Evgenii Nikishin, Shantanu Thakoor, Tingfung Lau, Stefano Ermon
Adversarial Example Token Correlation

December 11, 2021

Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting
Junhua Zou, Zhisong Pan, Junyang Qiu, Xin Liu, Ting Rui, Wei Li
Adversarial Example Task Transferability Gradient Based Attack Region Prediction Resized Diverse Input

December 10, 2021

December 9, 2021

December 6, 2021

Adversarial Machine Learning In Network Intrusion Detection Domain: A Systematic Review
Huda Ali Alatwi, Charles Morisset
Deep Learning Model Adversarial Example Adversarial Learning Systematic Review Network Intrusion General Adversarial

December 2, 2021

December 1, 2021

Adversarial Example

Papers

A Theoretical View of Linear Backpropagation and Its Convergence

Certified Federated Adversarial Training

Explain, Edit, and Understand: Rethinking User Study Design for Evaluating Model Explanations

DuQM: A Chinese Dataset of Linguistically Perturbed Natural Questions for Evaluating the Robustness of Question Matching Models

On the Convergence and Robustness of Adversarial Training

Adversarial Examples for Extreme Multilabel Text Classification

Robustifying automatic speech recognition by extracting slowly varying features

Triangle Attack: A Query-efficient Decision-based Adversarial Attack

Detecting Audio Adversarial Examples with Logit Noising

Quantifying and Understanding Adversarial Examples in Discrete Input Spaces

Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting

Cross-Modal Transferable Adversarial Attacks from Images to Videos

RamBoAttack: A Robust Query Efficient Deep Neural Network Decision Exploit

Mutual Adversarial Training: Learning together is better than going alone

PARL: Enhancing Diversity of Ensemble Networks to Resist Adversarial Attacks via Pairwise Adversarially Robust Loss Function

Adversarial Machine Learning In Network Intrusion Detection Domain: A Systematic Review

A Unified Framework for Adversarial Attack and Defense in Constrained Feature Space

Adversarial Robustness of Deep Reinforcement Learning based Dynamic Recommender Systems

$\ell_\infty$-Robustness and Beyond: Unleashing Efficient Adversarial Training

Push Stricter to Decide Better: A Class-Conditional Feature Adaptive Framework for Improving Adversarial Robustness