Adversarial Noise

Adversarial noise refers to carefully crafted perturbations added to data to mislead machine learning models, primarily deep neural networks. Current research focuses on detecting and mitigating these attacks across various modalities (images, audio, text), employing techniques like generative models (diffusion models), variational sparsification, and biologically-inspired feature extraction to enhance robustness. This field is crucial for ensuring the reliability and security of AI systems in diverse applications, from facial recognition and autonomous driving to medical image analysis and speech recognition, where vulnerabilities to adversarial manipulation can have significant consequences.

Papers

February 21, 2023

Interpretable Spectrum Transformation Attacks to Speaker Recognition
Jiadi Yao, Hong Luo, Xiao-Lei Zhang
Adversarial Attack Speaker Recognition Adversarial Noise Spectral Domain Attack

December 10, 2022

Targeted Adversarial Attacks on Deep Reinforcement Learning Policies via Model Checking
Dennis Gross, Thiago D. Simao, Nils Jansen, Guillermo A. Perez
Adversarial Attack Deep Reinforcement Learning Adversarial Noise Model Checking Optimal Adversarial

November 19, 2022

Phonemic Adversarial Attack against Audio Recognition in Real World
Jiakai Wang, Zhendong Chen, Zixin Yin, Qinghong Yang, Xianglong Liu
Adversarial Attack Fine Grained Real World Adversarial Noise Audio Recognition

November 3, 2022

Robust Few-shot Learning Without Using any Adversarial Samples
Gaurav Kumar Nayak, Ruchit Rawal, Inder Khatri, Anirban Chakraborty
Meta Learning Adversarial Sample Adversarial Noise Adversarial Evaluation ROBust Few Shot

October 26, 2022

There is more than one kind of robustness: Fooling Whisper with adversarial examples
Raphael Olivier, Bhiksha Raj
Native Robustness Automatic Speech Recognition Adversarial Example Speech Recognition Adversarial Noise State of the Art Whisper Open Whisper Style Speech Model Whisper Model

October 13, 2022

Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face Recognition
Shuai Jia, Bangjie Yin, Taiping Yao, Shouhong Ding, Chunhua Shen, Xiaokang Yang, Chao Ma
Adversarial Attack Face Recognition Adversarial Noise Rich Attribute Transferable Adversarial Attack Adversarial Feature Attribute Selection

August 17, 2022

Analyzing Robustness of End-to-End Neural Models for Automatic Speech Recognition
Goutham Rajendran, Wei Zou
Native Robustness Automatic Speech Recognition Adversarial Noise Wav2Vec2 Model

August 14, 2022

Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attacks
Tian Yu Liu, Yu Yang, Baharan Mirzasoleiman
Adversarial Perturbation Adversarial Noise Data Poisoning Attack Defense Method Backdoor Poisoning Attack

July 25, 2022

Improving Adversarial Robustness via Mutual Information Estimation
Dawei Zhou, Nannan Wang, Xinbo Gao, Bo Han, Xiaoyu Wang, Yibing Zhan, Tongliang Liu
Adversarial Robustness Adversarial DEfense Adversarial Noise Adversarial Pattern

June 27, 2022

Exact Spectral Norm Regularization for Neural Networks
Anton Johansson, Claes Strannegård, Niklas Engsner, Petter Mostad
Neural Network Adversarial Attack Adversarial Noise Spectral Regularization Spectral Norm Jacobian Regularization

June 17, 2022

Learning a Single Neuron with Adversarial Label Noise via Gradient Descent
Ilias Diakonikolas, Vasilis Kontonis, Christos Tzamos, Nikos Zarifis
Gradient Descent Adversarial Noise Convex Loss Single Neuron Monotone Neural Network

June 15, 2022

Corruption-Robust Contextual Search through Density Updates
Renato Paes Leme, Chara Podimata, Jon Schneider
Adversarial Noise Aware Query Dynamic Loss Symmetric Loss Local Density Tight Regret

June 10, 2022

Localized adversarial artifacts for compressed sensing MRI
Rima Alaifari, Giovanni S. Alberti, Tandri Gauksson
Native Robustness Magnetic Resonance Imaging Image Reconstruction Adversarial Noise Probabilistic Reconstruction Adversarial Object

June 9, 2022

Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks
Huishuai Zhang, Da Yu, Yiping Lu, Di He
Neural Network Adversarial Attack Adversarial Example Neural Tangent Kernel Adversarial Noise Gradient Method Random Neural Network

June 2, 2022

Adaptive Adversarial Training to Improve Adversarial Robustness of DNNs for Medical Image Segmentation and Detection
Linhai Ma, Liang Liang
Deep Neural Network Adversarial Attack Data Detection Adversarial Training Adversarial Robustness Medical Image Segmentation Adversarial Noise Adaptive Adversarial Training

June 1, 2022

Support Vector Machines under Adversarial Label Contamination
Huang Xiao, Battista Biggio, Blaine Nelson, Han Xiao, Claudia Eckert, Fabio Roli
Adversarial Noise Adversarial Scenario Adversarial Manipulation Secure Machine Learning

May 18, 2022

RandoMix: A mixed sample data augmentation method with multiple mixed modes
Xiaoliang Liu, Furao Shen, Jian Zhao, Changhai Nie
Data Augmentation Adversarial Noise Effective Data Augmentation Dual Mode Mixed Sample Data Augmentation

May 5, 2022

Structural Extensions of Basis Pursuit: Guarantees on Adversarial Robustness
Dávid Szeghy, Mahmoud Aslan, Áron Fóthi, Balázs Mészáros, Zoltán Ádám Milacski, András Lőrincz
Adversarial Robustness Adversarial Noise Shallow Network Formal Guarantee Fast Gradient Sign Method Localized Sparse Incomplete Basis Pursuit

April 22, 2022

A Tale of Two Models: Constructing Evasive Attacks on Edge Models
Wei Hao, Aahil Awatramani, Jiayang Hu, Chengzhi Mao, Pin-Chun Chen, Eyal Cidon, Asaf Cidon, Junfeng Yang
Full Model Adversarial Noise Cautionary TALE Evasion Attack Edge Model Edge Based Edge Attribute

April 6, 2022

Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training
Yuanhao Cai, Xiaowan Hu, Haoqian Wang, Yulun Zhang, Hanspeter Pfister, Donglai Wei
LeArning Abstract Adversarial Noise Noisy Image