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 1751–1800 of 1808 papers

TitleStatusHype
Structured Adversarial Attack: Towards General Implementation and Better InterpretabilityCode0
Rob-GAN: Generator, Discriminator, and Adversarial AttackerCode0
Evaluating and Understanding the Robustness of Adversarial Logit PairingCode0
Harmonic Adversarial Attack Method—0
With Friends Like These, Who Needs Adversaries?Code0
A Game-Based Approximate Verification of Deep Neural Networks with Provable GuaranteesCode0
Adaptive Adversarial Attack on Scene Text Recognition—0
Adversarial Examples in Deep Learning: Characterization and Divergence—0
Learning Visually-Grounded Semantics from Contrastive Adversarial SamplesCode0
Evaluation of Momentum Diverse Input Iterative Fast Gradient Sign Method (M-DI2-FGSM) Based Attack Method on MCS 2018 Adversarial Attacks on Black Box Face Recognition System—0
Adversarial Attack on Graph Structured DataCode0
An Explainable Adversarial Robustness Metric for Deep Learning Neural Networks—0
Adversarial Attacks on Face Detectors using Neural Net based Constrained Optimization—0
Sequential Attacks on Agents for Long-Term Adversarial Goals—0
ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audio—0
GenAttack: Practical Black-box Attacks with Gradient-Free OptimizationCode0
Knowledge Distillation with Adversarial Samples Supporting Decision BoundaryCode0
ADef: an Iterative Algorithm to Construct Adversarial DeformationsCode0
ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object DetectorCode0
An ADMM-Based Universal Framework for Adversarial Attacks on Deep Neural Networks—0
Learn To Pay AttentionCode0
Protection against Cloning for Deep Learning—0
Adversarial Defense based on Structure-to-Signal Autoencoders—0
DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems—0
Improving Transferability of Adversarial Examples with Input DiversityCode0
Vulnerability of Deep Learning—0
Defending against Adversarial Attack towards Deep Neural Networks via Collaborative Multi-task Training—0
ASP:A Fast Adversarial Attack Example Generation Framework based on Adversarial Saliency Prediction—0
Security Analysis and Enhancement of Model Compressed Deep Learning Systems under Adversarial Attacks—0
Blind Pre-Processing: A Robust Defense Method Against Adversarial Examples—0
Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial ExamplesCode0
Certified Defenses against Adversarial ExamplesCode0
Deflecting Adversarial Attacks with Pixel DeflectionCode0
Query-Efficient Black-box Adversarial Examples (superceded)Code0
Defense against Adversarial Attacks Using High-Level Representation Guided DenoiserCode0
Model Extraction Warning in MLaaS Paradigm—0
Linear system security -- detection and correction of adversarial attacks in the noise-free case—0
Provable defenses against adversarial examples via the convex outer adversarial polytopeCode0
Generating Natural Adversarial ExamplesCode0
Boosting Adversarial Attacks with MomentumCode0
Standard detectors aren't (currently) fooled by physical adversarial stop signs—0
Resilient Learning-Based Control for Synchronization of Passive Multi-Agent Systems under Attack—0
EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial ExamplesCode0
ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute ModelsCode0
Class-based Prediction Errors to Detect Hate Speech with Out-of-vocabulary Words—0
Adversarial-Playground: A Visualization Suite Showing How Adversarial Examples Fool Deep LearningCode0
Adversarial and Clean Data Are Not TwinsCode0
Biologically inspired protection of deep networks from adversarial attacks—0
Tactics of Adversarial Attack on Deep Reinforcement Learning Agents—0
On Detecting Adversarial PerturbationsCode0
Show:102550
← PrevPage 36 of 37Next →
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