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

October 27, 2022

October 26, 2022

October 22, 2022

ADDMU: Detection of Far-Boundary Adversarial Examples with Data and Model Uncertainty Estimation
Fan Yin, Yao Li, Cho-Jui Hsieh, Kai-Wei Chang
Adversarial Attack Adversarial Example Data Detection Raw Data Model Uncertainty Adversarial Search

October 21, 2022

Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks
Jiyang Guan, Jian Liang, Ran He
Adversarial Example Full Model Correlation Analysis Suspect Model DNN Fingerprint Removal Attack

October 20, 2022

October 19, 2022

Effective Targeted Attacks for Adversarial Self-Supervised Learning
Minseon Kim, Hyeonjeong Ha, Sooel Son, Sung Ju Hwang
Adversarial Attack Adversarial Example Adversarial Training Attack Strategy Untargeted Adversarial Attack

October 17, 2022

October 16, 2022

Nowhere to Hide: A Lightweight Unsupervised Detector against Adversarial Examples
Hui Liu, Bo Zhao, Kehuan Zhang, Peng Liu
Adversarial Example Adversarial Image Adversarial Detection Unsupervised Detection

October 11, 2022

What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness?
Nikolaos Tsilivis, Julia Kempe
Adversarial Example Adversarial Robustness Neural Tangent Kernel Adversarial Vulnerability

October 9, 2022

October 7, 2022

Adversarially Robust Prototypical Few-shot Segmentation with Neural-ODEs
Prashant Pandey, Aleti Vardhan, Mustafa Chasmai, Tanuj Sur, Brejesh Lall
Adversarial Attack Adversarial Example Adversarial Training Neural ODE Shot Segmentation

Adversarial Example

Papers

TAD: Transfer Learning-based Multi-Adversarial Detection of Evasion Attacks against Network Intrusion Detection Systems

Isometric 3D Adversarial Examples in the Physical World

There is more than one kind of robustness: Fooling Whisper with adversarial examples

BioNLI: Generating a Biomedical NLI Dataset Using Lexico-semantic Constraints for Adversarial Examples

Improving Adversarial Robustness via Joint Classification and Multiple Explicit Detection Classes

Adversarially Robust Medical Classification via Attentive Convolutional Neural Networks

Adversarial Purification with the Manifold Hypothesis

ADDMU: Detection of Far-Boundary Adversarial Examples with Data and Model Uncertainty Estimation

Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks

Identifying Human Strategies for Generating Word-Level Adversarial Examples

Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models

Effective Targeted Attacks for Adversarial Self-Supervised Learning

Towards Generating Adversarial Examples on Mixed-type Data

Probabilistic Categorical Adversarial Attack & Adversarial Training

Differential Evolution based Dual Adversarial Camouflage: Fooling Human Eyes and Object Detectors

Nowhere to Hide: A Lightweight Unsupervised Detector against Adversarial Examples

What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness?

Pruning Adversarially Robust Neural Networks without Adversarial Examples

Towards Understanding and Boosting Adversarial Transferability from a Distribution Perspective

Adversarially Robust Prototypical Few-shot Segmentation with Neural-ODEs