Adversarial-Attack-Methods-Summary

News

🔥[2024-07-24] Papers of ICML 2024 have been updated here!

🔥[2024-07-04] Papers of CVPR 2024 have been updated here!

2023

Title	Publish	Repo	Paper	Summary
Content-based Unrestricted Adversarial Attack	NeurIPS	-		summary
Diff-PGD: Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability	NeurIPS			summary
Downstream-agnostic Adversarial Examples	ICCV
AdvDiffuser: Natural Adversarial Example Synthesis with Diffusion Models	ICCV			summary
Frequency-aware GAN for Adversarial Manipulation Generation	ICCV	-
AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models	-			summary
Diffusion Models for Imperceptible and Transferable Adversarial Attack	-
Improving Adversarial Transferability by Stable Diffusion	-	-
Semantic Adversarial Attacks via Diffusion Models	BMVC			summary

2022

Title	Publish	Repo	Paper	Summary
SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness	ECCV			-
Natural color fool: Towards boosting black-box unrestricted attacks	NeurIPS	-	-	-
Sparse Black-Box Video Attack with Reinforcement Learning	IJCV
Attacking Video Recognition Models with Bullet-Screen Comments	AAAI

2021

Title	Publish	Repo	Paper	Summary
Towards Feature Space Adversarial Attack	**			summary

2020

Title	Publish	Repo	Paper	Summary
Unrestricted Adversarial Examples via Semantic Manipulation	ICLR			summary
SemanticAdv: Generating Adversarial Examples via Attribute-conditioned Image Editing	ECCV			summary
Colorfool: Semantic adversarial colorization	CVPR	-	-	-

2019

Title	Publish	Repo	Paper	Summary
Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifiers	ICCV			summary
Rob-GAN: Generator, Discriminator, and Adversarial Attacker	CVPR			summary
ADef: an Iterative Algorithm to Construct Adversarial Deformations	ICLR	-	-	-
AdvGAN++: Harnessing Latent Layers for Adversary Generation	CVPRW			summary
One pixel attack for fooling deep neural networks	IEEE TEVC	-	-	-

~2018

Title	Publish	Repo	Paper	Summary
Intriguing Properties of Neural Networks.	ICLR 2014	-		summary
FGSM: Explaining and Harnessing Adversarial Examples	ICLR 2015	-		summary
Deepfool: a simple and accurate method to fool deep neural networks	CVPR 2016			-
Universal adversarial perturbations	CVPR 2017	-
Towards evaluating the robustness of neural networks	2017 IEEE Symposium on Security and Privacy (SP)	-	-	-
Ensemble Adversarial Training: Attacks and Defenses	ICLR 2018	-		-
PGD: Towards Deep Learning Models Resistant to Adversarial Attacks	ICLR 2018			-
Generating Natural Adversarial Examples	ICLR 2018			summary
Constructing Unrestricted Adversarial Examples with Generative Models	NeurIPS 2018			summary
NAG: Network for Adversary Generation	CVPR 2018			summary
Semantic Adversarial Examples	CVPRW 2018			summary
AdvGAN: Generating adversarial examples with adversarial networks	IJCAI 2018			summary
ATN: Learning to Attack: Adversarial Transformation Networks	AAAI 2018			summary