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 641–650 of 1808 papers

Title	Date	Tasks	Status	Hype	Score
Exploring the Vulnerability of Natural Language Processing Models via Universal Adversarial Texts	Dec 1, 2021	Adversarial Attacktext-classification	CodeCode Available	0	5
Fast Adversarial CNN-based Perturbation Attack of No-Reference Image Quality Metrics	Apr 11, 2023	Adversarial AttackNo-Reference Image Quality Assessment	CodeCode Available	0	5
FireBERT: Hardening BERT-based classifiers against adversarial attack	Aug 10, 2020	Adversarial Attack	CodeCode Available	0	5
Disrupting Deep Uncertainty Estimation Without Harming Accuracy	Oct 26, 2021	Adversarial Attack	CodeCode Available	0	5
EvoBA: An Evolution Strategy as a Strong Baseline forBlack-Box Adversarial Attacks	Jul 12, 2021	Adversarial Attack	CodeCode Available	0	5
REGroup: Rank-aggregating Ensemble of Generative Classifiers for Robust Predictions	Jun 18, 2020	Adversarial Attack	CodeCode Available	0	5
Adversarial Attack and Defense on Graph Data: A Survey	Dec 26, 2018	Adversarial Attackimage-classification	CodeCode Available	0	5
Task-generalizable Adversarial Attack based on Perceptual Metric	Nov 22, 2018	Adversarial Attackobject-detection	CodeCode Available	0	5
Exacerbating Algorithmic Bias through Fairness Attacks	Dec 16, 2020	Adversarial AttackBIG-bench Machine Learning	CodeCode Available	0	5
Controversial stimuli: pitting neural networks against each other as models of human recognition	Nov 21, 2019	Adversarial Attack	CodeCode Available	0	5

Show:10 25 50

← PrevPage 65 of 181Next →

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