Adversarial Attack

An Adversarial Attack is a technique to find a perturbation that changes the prediction of a machine learning model. The perturbation can be very small and imperceptible to human eyes.

Source: Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1251–1275 of 1808 papers

Title	Date	Tasks	Status	Hype
Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification	Dec 21, 2020	Adversarial AttackBackdoor Attack	CodeCode Available	1
Variational Quantum Cloning: Improving Practicality for Quantum Cryptanalysis	Dec 21, 2020	Adversarial AttackCryptanalysis	—Unverified	0
Exploiting Vulnerability of Pooling in Convolutional Neural Networks by Strict Layer-Output Manipulation for Adversarial Attacks	Dec 21, 2020	Adversarial AttackDimensionality Reduction	—Unverified	0
Blurring Fools the Network -- Adversarial Attacks by Feature Peak Suppression and Gaussian Blurring	Dec 21, 2020	Adversarial Attack	—Unverified	0
Efficient Training of Robust Decision Trees Against Adversarial Examples	Dec 18, 2020	Adversarial Attack	CodeCode Available	1
A Hierarchical Feature Constraint to Camouflage Medical Adversarial Attacks	Dec 17, 2020	Adversarial AttackDecision Making	CodeCode Available	0
Exacerbating Algorithmic Bias through Fairness Attacks	Dec 16, 2020	Adversarial AttackBIG-bench Machine Learning	CodeCode Available	0
A Distributed Black-Box Adversarial Attack Based on Multi-Group Particle Swarm Optimization	Dec 14, 2020	Adversarial Attack	CodeCode Available	0
Disentangled Information Bottleneck	Dec 14, 2020	Adversarial AttackOut-of-Distribution Detection	CodeCode Available	1
Blindfolded Attackers Still Threatening: Strict Black-Box Adversarial Attacks on Graphs	Dec 12, 2020	Adversarial AttackGraph Classification	—Unverified	0
Attack Agnostic Detection of Adversarial Examples via Random Subspace Analysis	Dec 11, 2020	Adversarial AttackAdversarial Attack Detection	—Unverified	0
Composite Adversarial Attacks	Dec 10, 2020	Adversarial AttackAdversarial Robustness	CodeCode Available	1
SPAA: Stealthy Projector-based Adversarial Attacks on Deep Image Classifiers	Dec 10, 2020	Adversarial Attack	CodeCode Available	1
Geometric Adversarial Attacks and Defenses on 3D Point Clouds	Dec 10, 2020	Adversarial AttackAdversarial Defense	CodeCode Available	1
Generating Out of Distribution Adversarial Attack using Latent Space Poisoning	Dec 9, 2020	Adversarial Attack	—Unverified	0
Using Feature Alignment Can Improve Clean Average Precision and Adversarial Robustness in Object Detection	Dec 8, 2020	2D Object DetectionAdversarial Attack	CodeCode Available	1
Towards Natural Robustness Against Adversarial Examples	Dec 4, 2020	Adversarial Attack	—Unverified	0
FenceBox: A Platform for Defeating Adversarial Examples with Data Augmentation Techniques	Dec 3, 2020	Adversarial AttackData Augmentation	CodeCode Available	0
Channel Effects on Surrogate Models of Adversarial Attacks against Wireless Signal Classifiers	Dec 3, 2020	Adversarial Attack	—Unverified	0
Enhancing Neural Models with Vulnerability via Adversarial Attack	Dec 1, 2020	Adversarial AttackSentence	CodeCode Available	0
Contrastive Zero-Shot Learning for Cross-Domain Slot Filling with Adversarial Attack	Dec 1, 2020	Adversarial Attackslot-filling	—Unverified	0
Adversarial Attacks on Deep Graph Matching	Dec 1, 2020	Adversarial AttackDensity Estimation	—Unverified	0
Adversarial Learning for Robust Deep Clustering	Dec 1, 2020	Adversarial AttackClustering	CodeCode Available	1
Just One Moment: Structural Vulnerability of Deep Action Recognition against One Frame Attack	Nov 30, 2020	Action RecognitionAdversarial Attack	—Unverified	0
Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses	Nov 30, 2020	Adversarial AttackAdversarial Defense	CodeCode Available	1

Show:10 25 50

← PrevPage 51 of 73Next →

All datasets CIFAR-10 CIFAR-100

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Xu et al.	Attack: PGD20	78.68	—	Unverified
2	3-ensemble of multi-resolution self-ensembles	Attack: AutoAttack	78.13	—	Unverified
3	TRADES-ANCRA/ResNet18	Attack: AutoAttack	59.7	—	Unverified
4	AdvTraining [madry2018]	Attack: PGD20	48.44	—	Unverified
5	TRADES [zhang2019b]	Attack: PGD20	45.9	—	Unverified
6	XU-Net	Robust Accuracy	1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	3-ensemble of multi-resolution self-ensembles	Attack: AutoAttack	51.28	—	Unverified
2	multi-resolution self-ensembles	Attack: AutoAttack	47.85	—	Unverified