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 1751–1775 of 1808 papers

Title	Date	Tasks	Status	Hype
Adaptive Adversarial Attack on Scene Text Recognition	Jul 9, 2018	Adversarial Attackimage-classification	—Unverified	0
Local Gradients Smoothing: Defense against localized adversarial attacks	Jul 3, 2018	Adversarial Attack	CodeCode Available	1
Adversarial Examples in Deep Learning: Characterization and Divergence	Jun 29, 2018	Adversarial AttackDeep Learning	—Unverified	0
Learning Visually-Grounded Semantics from Contrastive Adversarial Samples	Jun 27, 2018	Adversarial AttackImage Captioning	CodeCode Available	0
Evaluation of Momentum Diverse Input Iterative Fast Gradient Sign Method (M-DI2-FGSM) Based Attack Method on MCS 2018 Adversarial Attacks on Black Box Face Recognition System	Jun 23, 2018	Adversarial AttackFace Recognition	—Unverified	0
Adversarial Attack on Graph Structured Data	Jun 6, 2018	Adversarial AttackGraph Neural Network	CodeCode Available	0
An Explainable Adversarial Robustness Metric for Deep Learning Neural Networks	Jun 5, 2018	Adversarial AttackAdversarial Robustness	—Unverified	0
Sequential Attacks on Agents for Long-Term Adversarial Goals	May 31, 2018	Adversarial AttackReinforcement Learning	—Unverified	0
Adversarial Attacks on Face Detectors using Neural Net based Constrained Optimization	May 31, 2018	Adversarial Attackimage-classification	—Unverified	0
ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audio	May 30, 2018	Adversarial AttackAudio Compression	—Unverified	0
GenAttack: Practical Black-box Attacks with Gradient-Free Optimization	May 28, 2018	Adversarial AttackAdversarial Robustness	CodeCode Available	0
Knowledge Distillation with Adversarial Samples Supporting Decision Boundary	May 15, 2018	Adversarial AttackKnowledge Distillation	CodeCode Available	0
ADef: an Iterative Algorithm to Construct Adversarial Deformations	Apr 20, 2018	Adversarial AttackGeneral Classification	CodeCode Available	0
ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector	Apr 16, 2018	Adversarial AttackAutonomous Vehicles	CodeCode Available	0
An ADMM-Based Universal Framework for Adversarial Attacks on Deep Neural Networks	Apr 9, 2018	Adversarial Attack	—Unverified	0
Learn To Pay Attention	Apr 6, 2018	Adversarial AttackGeneral Classification	CodeCode Available	0
Protection against Cloning for Deep Learning	Mar 29, 2018	Adversarial AttackDeep Learning	—Unverified	0
Adversarial Defense based on Structure-to-Signal Autoencoders	Mar 21, 2018	Adversarial AttackAdversarial Defense	—Unverified	0
DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems	Mar 20, 2018	Adversarial AttackDeep Learning	—Unverified	0
Improving Transferability of Adversarial Examples with Input Diversity	Mar 19, 2018	Adversarial AttackDiversity	CodeCode Available	0
Vulnerability of Deep Learning	Mar 16, 2018	Adversarial AttackDeep Learning	—Unverified	0
Defending against Adversarial Attack towards Deep Neural Networks via Collaborative Multi-task Training	Mar 14, 2018	Adversarial Attack	—Unverified	0
ASP:A Fast Adversarial Attack Example Generation Framework based on Adversarial Saliency Prediction	Feb 15, 2018	Adversarial Attackimage-classification	—Unverified	0
Security Analysis and Enhancement of Model Compressed Deep Learning Systems under Adversarial Attacks	Feb 14, 2018	Adversarial Attack	—Unverified	0
Blind Pre-Processing: A Robust Defense Method Against Adversarial Examples	Feb 5, 2018	Adversarial Attack	—Unverified	0

Show:10 25 50

← PrevPage 71 of 73Next →

All datasets CIFAR-10 CIFAR-100

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	ResNet20	Test Accuracy	89.95	89.95(1)	Community Verified
2	Xu et al.	Attack: PGD20	78.68	—	Unverified
3	3-ensemble of multi-resolution self-ensembles	Attack: AutoAttack	78.13	—	Unverified
4	TRADES-ANCRA/ResNet18	Attack: AutoAttack	59.7	—	Unverified
5	AdvTraining [madry2018]	Attack: PGD20	48.44	—	Unverified
6	TRADES [zhang2019b]	Attack: PGD20	45.9	—	Unverified
7	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