SOTAVerified|Agents Browse Leaderboard About

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 121–130 of 1808 papers

Title	Date	Tasks	Status	Hype
Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation	Oct 12, 2022	Adversarial Attack	CodeCode Available	1
Natural Color Fool: Towards Boosting Black-box Unrestricted Attacks	Oct 5, 2022	Adversarial Attack	CodeCode Available	1
Physical Adversarial Attack meets Computer Vision: A Decade Survey	Sep 30, 2022	Adversarial AttackMedical Diagnosis	CodeCode Available	1
Hiding Visual Information via Obfuscating Adversarial Perturbations	Sep 30, 2022	Adversarial AttackDe-identification	CodeCode Available	1
Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning	Sep 24, 2022	Adversarial Attack	CodeCode Available	1
Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking Models	Sep 14, 2022	Adversarial AttackLanguage Modelling	CodeCode Available	1
TSFool: Crafting Highly-Imperceptible Adversarial Time Series through Multi-Objective Attack	Sep 14, 2022	Adversarial Attackglobal-optimization	CodeCode Available	1
Scattering Model Guided Adversarial Examples for SAR Target Recognition: Attack and Defense	Sep 11, 2022	Adversarial AttackAdversarial Robustness	CodeCode Available	1
Unrestricted Black-box Adversarial Attack Using GAN with Limited Queries	Aug 24, 2022	Adversarial AttackClassification	CodeCode Available	1
UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA	Aug 19, 2022	Adversarial AttackExplainable Models	CodeCode Available	1

Show:10 25 50

← PrevPage 13 of 181Next →

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