SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1631–1640 of 1808 papers

TitleStatusHype
Universal Adversarial Attack Using Very Few Test Examples—0
Debiasing Backdoor Attack: A Benign Application of Backdoor Attack in Eliminating Data Bias—0
Deceptive Diffusion: Generating Synthetic Adversarial Examples—0
Adversarial Attacks against Deep Saliency Models—0
A Branch and Bound Framework for Stronger Adversarial Attacks of ReLU Networks—0
Decoder Gradient Shield: Provable and High-Fidelity Prevention of Gradient-Based Box-Free Watermark Removal—0
Similarity of Neural Architectures using Adversarial Attack Transferability—0
Simple and Effective Stochastic Neural Networks—0
Deep adversarial attack on target detection systems—0
Deep-Attack over the Deep Reinforcement Learning—0
Show:102550
← PrevPage 164 of 181Next →
All datasetsCIFAR-10CIFAR-100

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Xu et al.Attack: PGD2078.68—Unverified
23-ensemble of multi-resolution self-ensemblesAttack: AutoAttack78.13—Unverified
3TRADES-ANCRA/ResNet18Attack: AutoAttack59.7—Unverified
4AdvTraining [madry2018]Attack: PGD2048.44—Unverified
5TRADES [zhang2019b]Attack: PGD2045.9—Unverified
6XU-NetRobust Accuracy1—Unverified
#ModelMetricClaimedVerifiedStatus
13-ensemble of multi-resolution self-ensemblesAttack: AutoAttack51.28—Unverified
2multi-resolution self-ensemblesAttack: AutoAttack47.85—Unverified