Adversarial Image

Adversarial images are subtly altered images designed to deceive deep learning models, primarily image classifiers and more recently, vision-language models, into making incorrect predictions while appearing normal to humans. Current research focuses on developing more robust and transferable adversarial attacks, exploring various attack methods (e.g., gradient-based, generative, and frequency-domain manipulations) and defense mechanisms (e.g., adversarial training, purification, and anomaly detection). This field is crucial for understanding and mitigating the vulnerabilities of AI systems to malicious manipulation, impacting the security and reliability of applications ranging from autonomous driving to medical image analysis.

Papers

July 13, 2022

Adversarially-Aware Robust Object Detector
Ziyi Dong, Pengxu Wei, Liang Lin
Adversarial Robustness Adversarial Image Robust Detection Robust Object Detection Adversarial Discriminator

July 11, 2022

Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation
Zhun Zhong, Yuyang Zhao, Gim Hee Lee, Nicu Sebe
Adversarial Training Synthetic to Real Adversarial Image Adversarial Feature Adversarial Style Augmentation Urban Scene Segmentation

June 17, 2022

Minimum Noticeable Difference based Adversarial Privacy Preserving Image Generation
Wen Sun, Jian Jin, Weisi Lin
Adversarial Example Loss Function Image Generation Adversarial Image Adversarial Loss Adversarial Generation Noticeable Difference

June 16, 2022

Using adversarial images to improve outcomes of federated learning for non-IID data
Anastasiya Danilenka, Maria Ganzha, Marcin Paprzycki, Jacek Mańdziuk
LeArning Abstract Imbalanced Data Adversarial Image Adversarial Input Multiple Outcome Non IID Data Skewed Non IID

June 3, 2022

The Importance of Image Interpretation: Patterns of Semantic Misclassification in Real-World Adversarial Images
Zhengyu Zhao, Nga Dang, Martha Larson
Real World Importance Aware Generative Adversarial Complex Pattern Adversarial Image Realistic Adversarial

May 26, 2022

MALICE: Manipulation Attacks on Learned Image ComprEssion
Kang Liu, Di Wu, Yiru Wang, Dan Feng, Benjamin Tan, Siddharth Garg
Adversarial Attack Image Compression Adversarial Image Joint Photographic Expert Group Learned Image Compression

March 26, 2022

Reverse Engineering of Imperceptible Adversarial Image Perturbations
Yifan Gong, Yuguang Yao, Yize Li, Yimeng Zhang, Xiaoming Liu, Xue Lin, Sijia Liu
Adversarial Attack Adversarial Perturbation Adversarial Image Reverse Engineering Imperceptible Adversarial Perturbation

March 19, 2022

Adversarial Defense via Image Denoising with Chaotic Encryption
Shi Hu, Eric Nalisnick, Max Welling
Adversarial Example Image Denoising Adversarial DEfense Adversarial Image Black Box Attack Gray Box Adversarial Evaluation Chaotic Behavior

March 17, 2022

Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Input
Junyoung Byun, Seungju Cho, Myung-Joon Kwon, Hee-Seon Kim, Changick Kim
Adversarial Example Task Transferability Adversarial Image Image Augmentation

March 14, 2022

Adversarial amplitude swap towards robust image classifiers
Chun Yang Tan, Kazuhiko Kawamoto, Hiroshi Kera
Native Robustness Image Classification Adversarial Perturbation Adversarial Image Robust Overfitting General Robustness Adversarial Covariate Shift

March 2, 2022

Benchmarking Robustness of Deep Learning Classifiers Using Two-Factor Perturbation
Wei Dai, Daniel Berleant
Native Robustness Adversarial Image Additive Perturbation Deep Learning Classifier Robustness Benchmark Adversarial Corruption Image Perturbation

February 2, 2022

An Eye for an Eye: Defending against Gradient-based Attacks with Gradients
Hanbin Hong, Yuan Hong, Yu Kong
Adversarial Attack Adversarial Image Human Eye Gradient Based Attack Stream Network

January 4, 2022

Towards Understanding and Harnessing the Effect of Image Transformation in Adversarial Detection
Hui Liu, Bo Zhao, Yuefeng Peng, Weidong Li, Peng Liu
Adversarial Attack Adversarial Example Mixed Effect Human Understanding Adversarial Image Image Transformation Adversarial Detection

December 29, 2021

December 28, 2021

Associative Adversarial Learning Based on Selective Attack
Runqi Wang, Xiaoyue Duan, Baochang Zhang, Song Xue, Wentao Zhu, David Doermann, Guodong Guo
Adversarial Robustness Adversarial Learning Adversarial Image Associative Recall

December 22, 2021

Detect & Reject for Transferability of Black-box Adversarial Attacks Against Network Intrusion Detection Systems
Islam Debicha, Thibault Debatty, Jean-Michel Dricot, Wim Mees, Tayeb Kenaza
Adversarial Attack Task Transferability Detection Model Network Intrusion Detection Adversarial Image Black Box Adversarial Attack Risky Prompt Rejection Learning Based Intrusion Detection Adversarial Traffic

December 16, 2021

All You Need is RAW: Defending Against Adversarial Attacks with Camera Image Pipelines
Yuxuan Zhang, Bo Dong, Felix Heide
Adversarial Attack Adversarial DEfense Adversarial Image Raw Text Agnostic Adversarial Camera Pipeline

November 25, 2021

Going Grayscale: The Road to Understanding and Improving Unlearnable Examples
Zhuoran Liu, Zhengyu Zhao, Alex Kolmus, Tijn Berns, Twan van Laarhoven, Tom Heskes, Martha Larson
Adversarial Training Human Understanding Adversarial Image Built Road Grayscale Image Unlearnable Example Imperceptible Perturbation Complex Convolutional