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 1501–1525 of 1808 papers

TitleStatusHype
Breaking BERT: Understanding its Vulnerabilities for Named Entity Recognition through Adversarial AttackCode0
HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on TextCode0
Enhanced countering adversarial attacks via input denoising and feature restoringCode0
Efficient Robust Conformal Prediction via Lipschitz-Bounded NetworksCode0
SignSGD with Federated Defense: Harnessing Adversarial Attacks through Gradient Sign DecodingCode0
Bounded Adversarial Attack on Deep Content FeaturesCode0
SimAug: Learning Robust Representations from 3D Simulation for Pedestrian Trajectory Prediction in Unseen CamerasCode0
An Adversarial Attack Analysis on Malicious Advertisement URL Detection FrameworkCode0
Similarity-based Gray-box Adversarial Attack Against Deep Face RecognitionCode0
Spatial-Frequency Discriminability for Revealing Adversarial PerturbationsCode0
Identifying Adversarially Attackable and Robust SamplesCode0
Towards Analyzing Semantic Robustness of Deep Neural NetworksCode0
Towards Practical Robustness Analysis for DNNs based on PAC-Model LearningCode0
Identifying the Smallest Adversarial Load Perturbations that Render DC-OPF InfeasibleCode0
Simple and Efficient Partial Graph Adversarial Attack: A New PerspectiveCode0
Functional Adversarial AttacksCode0
Efficient Project Gradient Descent for Ensemble Adversarial AttackCode0
Probing Unlearned Diffusion Models: A Transferable Adversarial Attack PerspectiveCode0
An Evasion Attack against Stacked Capsule AutoencoderCode0
Single-Class Target-Specific Attack against Interpretable Deep Learning SystemsCode0
An Adversarial Approach for Explaining the Predictions of Deep Neural NetworksCode0
A Multi-task Adversarial Attack Against Face AuthenticationCode0
In-distribution adversarial attacks on object recognition models using gradient-free searchCode0
Efficient Formal Safety Analysis of Neural NetworksCode0
Amoeba: Circumventing ML-supported Network Censorship via Adversarial Reinforcement LearningCode0
Show:102550
← PrevPage 61 of 73Next →
All datasetsCIFAR-10CIFAR-100

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet20Test Accuracy89.9589.95(1)Community Verified
2Xu et al.Attack: PGD2078.68—Unverified
33-ensemble of multi-resolution self-ensemblesAttack: AutoAttack78.13—Unverified
4TRADES-ANCRA/ResNet18Attack: AutoAttack59.7—Unverified
5AdvTraining [madry2018]Attack: PGD2048.44—Unverified
6TRADES [zhang2019b]Attack: PGD2045.9—Unverified
7XU-NetRobust Accuracy1—Unverified
#ModelMetricClaimedVerifiedStatus
13-ensemble of multi-resolution self-ensemblesAttack: AutoAttack51.28—Unverified
2multi-resolution self-ensemblesAttack: AutoAttack47.85—Unverified