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 141–150 of 1808 papers

Title	Date	Tasks	Status	Hype
Towards Adversarial Attack on Vision-Language Pre-training Models	Jun 19, 2022	Adversarial AttackAdversarial Robustness	CodeCode Available	1
Boosting the Adversarial Transferability of Surrogate Models with Dark Knowledge	Jun 16, 2022	Adversarial AttackFace Verification	CodeCode Available	1
Adversarial Vulnerability of Randomized Ensembles	Jun 14, 2022	Adversarial AttackAdversarial Robustness	CodeCode Available	1
Proximal Splitting Adversarial Attacks for Semantic Segmentation	Jun 14, 2022	Adversarial AttackSegmentation	CodeCode Available	1
NeuroUnlock: Unlocking the Architecture of Obfuscated Deep Neural Networks	Jun 1, 2022	Adversarial AttackGPU	CodeCode Available	1
On the Robustness of Safe Reinforcement Learning under Observational Perturbations	May 29, 2022	Adversarial Attackreinforcement-learning	CodeCode Available	1
Transferable Adversarial Attack based on Integrated Gradients	May 26, 2022	Adversarial Attack	CodeCode Available	1
Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks	May 24, 2022	Adversarial Attack	CodeCode Available	1
Recipe2Vec: Multi-modal Recipe Representation Learning with Graph Neural Networks	May 24, 2022	Adversarial AttackGraph Neural Network	CodeCode Available	1
Phrase-level Textual Adversarial Attack with Label Preservation	May 22, 2022	Adversarial AttackSentence	CodeCode Available	1

Show:10 25 50

← PrevPage 15 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