Imperceptible Adversarial Perturbation

Imperceptible adversarial perturbations are subtly altered inputs designed to mislead deep learning models while remaining undetectable to humans. Current research focuses on generating these perturbations for various modalities (images, audio, video) using techniques like generative adversarial networks, diffusion models, and evolutionary algorithms, often targeting specific model architectures or aiming for improved transferability across different models. This field is crucial for assessing and improving the robustness of AI systems in security-sensitive applications, impacting areas like facial recognition, image classification, and speech recognition, where vulnerabilities to such attacks pose significant risks.

Papers

July 31, 2022

Is current research on adversarial robustness addressing the right problem?
Ali Borji
Adversarial Robustness Right Problem Adversarial Vulnerability Imperceptible Adversarial Perturbation Image Distortion Imperceptible Perturbation Current Research

June 30, 2022

Detecting and Recovering Adversarial Examples from Extracting Non-robust and Highly Predictive Adversarial Perturbations
Mingyu Dong, Jiahao Chen, Diqun Yan, Jingxing Gao, Li Dong, Rangding Wang
Adversarial Example Data Detection Adversarial Perturbation Imperceptible Adversarial Perturbation Non Robust Adversarial Example Detection

June 14, 2022

Adversarial Vulnerability of Randomized Ensembles
Hassan Dbouk, Naresh R. Shanbhag
Adversarial Robustness Adversarial Perturbation Adversarial Vulnerability Ensemble Classifier Imperceptible Adversarial Perturbation Efficient Adversarial Attack

May 30, 2022

Guided Diffusion Model for Adversarial Purification
Jinyi Wang, Zhaoyang Lyu, Dahua Lin, Bo Dai, Hongfei Fu
Adversarial Attack Adversarial Perturbation Denoising Process Denoising Diffusion Probabilistic Model Guided Diffusion Imperceptible Adversarial Perturbation

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

Deep Learning Generalization, Extrapolation, and Over-parameterization
Roozbeh Yousefzadeh
Neural Network Strong Generalization Deep Network Adversarial Vulnerability Extrapolation Framework Neural Network Generalization Imperceptible Adversarial Perturbation Benign Over Parameterization

March 18, 2022

Self-Ensemble Adversarial Training for Improved Robustness
Hongjun Wang, Yisen Wang
Adversarial Attack Adversarial Training Adversarial Sample Better Robustness Imperceptible Adversarial Perturbation Ensemble Adversarial

March 9, 2022

Robust Federated Learning Against Adversarial Attacks for Speech Emotion Recognition
Yi Chang, Sofiane Laridi, Zhao Ren, Gregory Palmer, Björn W. Schuller, Marco Fisichella
Adversarial Attack Adversarial Training Speech Emotion Recognition Imperceptible Adversarial Perturbation

January 4, 2022

Towards Transferable Unrestricted Adversarial Examples with Minimum Changes
Fangcheng Liu, Chao Zhang, Hongyang Zhang
Adversarial Example Adversarial Perturbation Imperceptible Adversarial Perturbation Unrestricted Adversarial Small Change