bib_adversarial_examples

Literature collection of adversarial examples.

As continuation from this collection.

Papers

Surveys

2022

• IEEE ANOMALOUS INSTANCE DETECTION IN DEEP LEARNING: A SURVEY

2021

• Journal https://paperswithcode.com/paper/adversarial-attacks-and-defenses-on-graphs-a
• Countering Malicious DeepFakes: Survey, Battleground, and Horizon

2020

• IEEE Anomalous Example Detection in Deep Learning: A Survey

2018

• Adversarial Examples: Attacks and Defenses for Deep Learning, github
• Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

2017

• Towards Evaluating the Robustness of Neural Networks

Attacks

2021

• Preprint Membership Inference Attacks From First Principles
• Arxiv ASK: Adversarial Soft k-Nearest Neighbor Attack and Defense + Code

2017

• Reject Exploring the Space of Black-box Attacks on Deep Neural Networks

2016

• CVPR DeepFool: a simple and accurate method to fool deep neural networks

Detection

2021

• ICML + code A General Framework For Detecting Anomalous Inputs to DNN Classifiers + talk + slides
• ICME DefakeHop: A Light-Weight High-Performance Deepfake Detector
• Detecting Adversarial Examples with Bayesian Neural Network
• CVPR + code LiBRe: A Practical Bayesian Approach to Adversarial Detection
• Thesis Defense Methods for Convolutional Neural Networks Against Adversarial Attacks

2020

• Adversarial Detection and Correction by Matching Prediction Distributions

2019

• ICML The odds ard odd
• ICLR AD V-BNN: IMPROVED ADVERSARIAL DEFENSE THROUGH ROBUST BAYESIAN NEURAL NETWORK

2018

• NeurIPS Code + Trust Score

2017

• ICLR ON DETECTING ADVERSARIAL PERTURBATIONS
• arXiv Detecting Adversarial Samples from Artifacts + code + original code

2019

• CVPR Detection based Defense against Adversarial Examples from the Steganalysis Point of View
• NeurIPS Adversarial Examples Are Not Bugs, They Are Features

Adversarial Training

2021

• NeurIPS Do Wider Neural Networks Really Help Adversarial Robustness?
• ICML Meta Adversarial Training against Universal Patches
• ICML Adversarially Trained Neural Policies in the Fourier Domain

2019

• ICLR ROBUSTNESS MAY BE AT ODDS WITH ACCURACY

Detection in Image Segmentation

2022

• Preprint DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows
• Preprint Adversarial Examples on Segmentation Models Can be Easy to Transfer

2021

• IJCNN Studying the Transferability of Non-Targeted Adversarial Attacks

2018

• CVPR On the Robustness of Semantic Segmentation Models to Adversarial Attacks

Datasets

• https://github.com/MadryLab/constructed-datasets

Others

2022

• Preprint Evaluation of Neural Networks defenses and attacks using NDCG and reciprocal rank metrics
• Preprint Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions
• Prepring Gradients without Backpropagation

2020

• arXiv Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Optimization

2021

• CVPR Natural Adversarial Examples
• https://simons.berkeley.edu/sites/default/files/docs/11887/nn-simons-part2.pdf
• FFT slides
• Preprint Closer Look at the Transferability of Adversarial Examples: How They Fool Different Models Differently

2019

• NeurIPS A Fourier Perspective on Model Robustness in Computer Vision

• Understanding Benford’s law and its vulnerability in image forensics

Libs

• DeepRobust
• Innsight
• RobustBench
• AdverTorch
• MadryLab
• Foolbox

adversarial-attacks-and-defense

Links

• Adversarial Machine Learning Reading List by Nicholas Carlini
• A Complete List of All (arXiv) Adversarial Example Papers by Nicholas Carlini Stay Tuned