Adversarial Attack

Adversarial attacks aim to deceive machine learning models by subtly altering input data, causing misclassifications or other erroneous outputs. Current research focuses on developing more robust models and detection methods, exploring various attack strategies across different model architectures (including vision transformers, recurrent neural networks, and graph neural networks) and data types (images, text, signals, and tabular data). Understanding and mitigating these attacks is crucial for ensuring the reliability and security of AI systems in diverse applications, from autonomous vehicles to medical diagnosis and cybersecurity.

Papers

January 1, 2023

December 31, 2022

Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence
Han Fang, Jiyi Zhang, Yupeng Qiu, Ke Xu, Chengfang Fang, Ee-Chien Chang
Adversarial Attack Adversarial Example Visual Creation Forensic Analysis Noise Robust Loss

December 30, 2022

December 28, 2022

December 27, 2022

EDoG: Adversarial Edge Detection For Graph Neural Networks
Xiaojun Xu, Yue Yu, Hanzhang Wang, Alok Lal, Carl A. Gunter, Bo Li
Graph Neural Network Adversarial Attack Adversarial Edge

December 26, 2022

Simultaneously Optimizing Perturbations and Positions for Black-box Adversarial Patch Attacks
Xingxing Wei, Ying Guo, Jie Yu, Bo Zhang
Adversarial Attack Adversarial Patch Product Specific Position Information Additive Perturbation Adversarial Patch Attack Realistic Adversarial

December 22, 2022

Aliasing is a Driver of Adversarial Attacks
Adrián Rodríguez-Muñoz, Antonio Torralba
Adversarial Attack Adversarial Perturbation Perceptual Aliasing Anti Aliasing

December 21, 2022

A Theoretical Study of The Effects of Adversarial Attacks on Sparse Regression
Deepak Maurya, Jean Honorio
Adversarial Attack Mixed Effect Adversarial Perturbation Primal Dual Theoretical Analysis Sparse Regression Robust Algorithm Vector Regression Lasso Condition Number

December 20, 2022

December 15, 2022

December 14, 2022

December 13, 2022

Adversarial Attacks and Defences for Skin Cancer Classification
Vinay Jogani, Joy Purohit, Ishaan Shivhare, Samina Attari, Shraddha Surtkar
Adversarial Attack Adversarial Example Medical Image Classification Dermoscopic Image Adversarial Defense Skin Cancer Classification

Adversarial Attack

Papers

Generalizable Black-Box Adversarial Attack with Meta Learning

ExploreADV: Towards exploratory attack for Neural Networks

Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence

Guidance Through Surrogate: Towards a Generic Diagnostic Attack

Adversarial attacks and defenses on ML- and hardware-based IoT device fingerprinting and identification

Defense Against Adversarial Attacks on Audio DeepFake Detection

Adversarial Virtual Exemplar Learning for Label-Frugal Satellite Image Change Detection

Differentiable Search of Accurate and Robust Architectures

EDoG: Adversarial Edge Detection For Graph Neural Networks

Simultaneously Optimizing Perturbations and Positions for Black-box Adversarial Patch Attacks

Aliasing is a Driver of Adversarial Attacks

A Theoretical Study of The Effects of Adversarial Attacks on Sparse Regression

In and Out-of-Domain Text Adversarial Robustness via Label Smoothing

A Comprehensive Study of the Robustness for LiDAR-based 3D Object Detectors against Adversarial Attacks

Multi-head Uncertainty Inference for Adversarial Attack Detection

On Evaluating Adversarial Robustness of Chest X-ray Classification: Pitfalls and Best Practices

Alternating Objectives Generates Stronger PGD-Based Adversarial Attacks

SAIF: Sparse Adversarial and Imperceptible Attack Framework

Synthesis of Adversarial DDOS Attacks Using Tabular Generative Adversarial Networks

Adversarial Attacks and Defences for Skin Cancer Classification