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 276–300 of 1808 papers

Title	Date	Tasks	Status	Hype
RayS: A Ray Searching Method for Hard-label Adversarial Attack	Jun 23, 2020	Adversarial AttackHard-label Attack	CodeCode Available	1
Differentiable Language Model Adversarial Attacks on Categorical Sequence Classifiers	Jun 19, 2020	Adversarial AttackLanguage Modeling	CodeCode Available	1
Boosting Black-Box Attack with Partially Transferred Conditional Adversarial Distribution	Jun 15, 2020	Adversarial Attack	CodeCode Available	1
Adversarial Self-Supervised Contrastive Learning	Jun 13, 2020	Adversarial AttackContrastive Learning	CodeCode Available	1
Targeted Adversarial Perturbations for Monocular Depth Prediction	Jun 12, 2020	Adversarial AttackAdversarial Defense	CodeCode Available	1
Interpolation between Residual and Non-Residual Networks	Jun 10, 2020	Adversarial Attackimage-classification	CodeCode Available	1
Pick-Object-Attack: Type-Specific Adversarial Attack for Object Detection	Jun 5, 2020	Adversarial AttackImage Captioning	CodeCode Available	1
Defending and Harnessing the Bit-Flip Based Adversarial Weight Attack	Jun 1, 2020	Adversarial AttackBinarization	CodeCode Available	1
Benchmarking Adversarial Robustness on Image Classification	Jun 1, 2020	Adversarial AttackAdversarial Robustness	CodeCode Available	1
On Intrinsic Dataset Properties for Adversarial Machine Learning	May 19, 2020	Adversarial AttackAdversarial Robustness	CodeCode Available	1
Defending Your Voice: Adversarial Attack on Voice Conversion	May 18, 2020	Adversarial AttackVoice Conversion	CodeCode Available	1
Improve robustness of DNN for ECG signal classification:a noise-to-signal ratio perspective	May 18, 2020	Adversarial AttackAdversarial Robustness	CodeCode Available	1
Attacking Recommender Systems with Augmented User Profiles	May 17, 2020	Adversarial AttackGenerative Adversarial Network	CodeCode Available	1
BayesOpt Adversarial Attack	May 1, 2020	Adversarial AttackBayesian Optimisation	CodeCode Available	1
Sign Bits Are All You Need for Black-Box Attacks	May 1, 2020	Adversarial AttackAll	CodeCode Available	1
Towards Feature Space Adversarial Attack	Apr 26, 2020	Adversarial AttackAdversarial Attack Detection	CodeCode Available	1
BERT-ATTACK: Adversarial Attack Against BERT Using BERT	Apr 21, 2020	Adversarial Attack	CodeCode Available	1
Adversarial Attack on Deep Learning-Based Splice Localization	Apr 17, 2020	Adversarial AttackAdversarial Robustness	CodeCode Available	1
Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking	Apr 8, 2020	Adversarial AttackPerson Re-Identification	CodeCode Available	1
Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible Noises	Mar 21, 2020	Adversarial Attack	CodeCode Available	1
Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior	Mar 17, 2020	Adversarial AttackVideo Classification	CodeCode Available	1
Disrupting Deepfakes: Adversarial Attacks Against Conditional Image Translation Networks and Facial Manipulation Systems	Mar 3, 2020	Adversarial AttackAttribute	CodeCode Available	1
Adversarial Ranking Attack and Defense	Feb 26, 2020	Adversarial AttackImage Retrieval	CodeCode Available	1
Stabilizing Differentiable Architecture Search via Perturbation-based Regularization	Feb 12, 2020	Adversarial AttackNeural Architecture Search	CodeCode Available	1
Watch out! Motion is Blurring the Vision of Your Deep Neural Networks	Feb 10, 2020	Adversarial AttackDeblurring	CodeCode Available	1

Show:10 25 50

← PrevPage 12 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