Adversarial Example Detection

Adversarial example detection aims to identify inputs maliciously crafted to fool machine learning models, a critical challenge for deploying these models in safety-critical applications. Current research focuses on improving the generalization ability of detectors across various attack types, exploring techniques like data reconstruction using variational autoencoders and leveraging features such as high-frequency image differences or even sentiment analysis of model internal representations. Effective adversarial example detection is crucial for enhancing the robustness and trustworthiness of machine learning systems, impacting fields ranging from autonomous driving to cybersecurity.

Papers

April 19, 2024

AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation
Heqi Peng, Yunhong Wang, Ruijie Yang, Beichen Li, Rui Wang, Yuanfang Guo
Adversarial Attack Adversarial Example Stronger Generalizability Domain Adversarial Adversarial Domain Adaptation Adversarial Example Detection

June 3, 2023

Towards Black-box Adversarial Example Detection: A Data Reconstruction-based Method
Yifei Gao, Zhiyu Lin, Yunfan Yang, Jitao Sang
Adversarial Example Raw Data Practical Method Adversarial Example Detection

May 8, 2023

Adversarial Examples Detection with Enhanced Image Difference Features based on Local Histogram Equalization
Zhaoxia Yin, Shaowei Zhu, Hang Su, Jianteng Peng, Wanli Lyu, Bin Luo
Adversarial Example Adversarial Perturbation Local Enhancement Histogram Equalization Image Difference Adversarial Example Detection

May 3, 2023

New Adversarial Image Detection Based on Sentiment Analysis
Yulong Wang, Tianxiang Li, Shenghong Li, Xin Yuan, Wei Ni
Adversarial Example Sentiment Analysis Adversarial Detection Adversarial Example Detection

November 10, 2022

Test-time adversarial detection and robustness for localizing humans using ultra wide band channel impulse responses
Abhiram Kolli, Muhammad Jehanzeb Mirza, Horst Possegger, Horst Bischof
Adversarial Attack Native Robustness Adversarial Example Real Human Adversarial Sample Test Time Adversarial Detection Adversarial Example Detection

August 31, 2022

Be Your Own Neighborhood: Detecting Adversarial Example by the Neighborhood Relations Built on Self-Supervised Learning
Zhiyuan He, Yijun Yang, Pin-Yu Chen, Qiang Xu, Tsung-Yi Ho
Deep Neural Network Self Supervised Learning Adversarial Example Adversarial Text Thy Neighbor Adaptive Attack Adversarial Example Detection

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 27, 2022

Adversarial Example Detection in Deployed Tree Ensembles
Laurens Devos, Wannes Meert, Jesse Davis
Adversarial Example Ensemble Learning Tree Ensemble Adversarial Detection Adversarial Example Detection

Adversarial Example Detection

Papers

AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation

Towards Black-box Adversarial Example Detection: A Data Reconstruction-based Method

Adversarial Examples Detection with Enhanced Image Difference Features based on Local Histogram Equalization

New Adversarial Image Detection Based on Sentiment Analysis

Test-time adversarial detection and robustness for localizing humans using ultra wide band channel impulse responses

Be Your Own Neighborhood: Detecting Adversarial Example by the Neighborhood Relations Built on Self-Supervised Learning

Detecting and Recovering Adversarial Examples from Extracting Non-robust and Highly Predictive Adversarial Perturbations

Adversarial Example Detection in Deployed Tree Ensembles