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 651–660 of 1808 papers

Title	Date	Tasks	Status	Hype
Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization	Apr 11, 2022	Adversarial AttackObject	—Unverified	0
DLOVE: A new Security Evaluation Tool for Deep Learning Based Watermarking Techniques	Jul 9, 2024	Adversarial AttackImage Manipulation	—Unverified	0
DMS: Addressing Information Loss with More Steps for Pragmatic Adversarial Attacks	Jun 9, 2024	Adversarial Attack	—Unverified	0
DO-AutoEncoder: Learning and Intervening Bivariate Causal Mechanisms in Images	Sep 25, 2019	Adversarial AttackRepresentation Learning	—Unverified	0
Democratic Training Against Universal Adversarial Perturbations	Feb 8, 2025	Adversarial Attack	—Unverified	0
Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?	Dec 4, 2024	Adversarial Attack	—Unverified	0
Evaluating Neural Model Robustness for Machine Comprehension	Apr 1, 2021	Adversarial Attackmodel	—Unverified	0
DoPa: A Comprehensive CNN Detection Methodology against Physical Adversarial Attacks	May 21, 2019	Adversarial AttackAdversarial Attack Detection	—Unverified	0
Doppelganger Method: Breaking Role Consistency in LLM Agent via Prompt-based Transferable Adversarial Attack	Jun 17, 2025	Adversarial AttackPrompt Engineering	—Unverified	0
Analyzing the Noise Robustness of Deep Neural Networks	Jan 26, 2020	Adversarial Attack	—Unverified	0

Show:10 25 50

← PrevPage 66 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