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 501–510 of 1808 papers

Title	Date	Tasks	Status	Hype
PhantomSound: Black-Box, Query-Efficient Audio Adversarial Attack via Split-Second Phoneme Injection	Sep 13, 2023	Adversarial AttackSpeech-to-Text	—Unverified	0
RAIN: Your Language Models Can Align Themselves without Finetuning	Sep 13, 2023	Adversarial AttackTruthfulQA	CodeCode Available	1
Outlier Robust Adversarial Training	Sep 10, 2023	Adversarial AttackBinary Classification	CodeCode Available	0
Certifying LLM Safety against Adversarial Prompting	Sep 6, 2023	Adversarial AttackLanguage Modelling	CodeCode Available	1
Adaptive Adversarial Training Does Not Increase Recourse Costs	Sep 5, 2023	Adversarial Attack	—Unverified	0
MathAttack: Attacking Large Language Models Towards Math Solving Ability	Sep 4, 2023	Adversarial AttackGSM8K	—Unverified	0
Improving Visual Quality and Transferability of Adversarial Attacks on Face Recognition Simultaneously with Adversarial Restoration	Sep 4, 2023	Adversarial AttackFace Recognition	—Unverified	0
Non-Asymptotic Bounds for Adversarial Excess Risk under Misspecified Models	Sep 2, 2023	Adversarial Attackregression	—Unverified	0
The Power of MEME: Adversarial Malware Creation with Model-Based Reinforcement Learning	Aug 31, 2023	Adversarial Attack	CodeCode Available	0
Can We Rely on AI?	Aug 29, 2023	Adversarial Attack	—Unverified	0

Show:10 25 50

← PrevPage 51 of 181Next →

All datasets CIFAR-10 CIFAR-100

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	ResNet20	Test Acc	90.1	90.1(1)	Community Verified
2	ResNet20	Test Accuracy	89.95	89.95(1)	Community Verified
3	ResNet20	Test Acc	89.5	90.1(1)	Community Verified
4	Xu et al.	Attack: PGD20	78.68	—	Unverified
5	3-ensemble of multi-resolution self-ensembles	Attack: AutoAttack	78.13	—	Unverified
6	TRADES-ANCRA/ResNet18	Attack: AutoAttack	59.7	—	Unverified
7	AdvTraining [madry2018]	Attack: PGD20	48.44	—	Unverified
8	TRADES [zhang2019b]	Attack: PGD20	45.9	—	Unverified
9	XU-Net	Robust Accuracy	1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ResNet20	Test Acc	80.4	—	Community Verified
2	3-ensemble of multi-resolution self-ensembles	Attack: AutoAttack	51.28	—	Unverified
3	multi-resolution self-ensembles	Attack: AutoAttack	47.85	—	Unverified