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

Showing 526550 of 1808 papers

TitleStatusHype
Gotta Catch 'Em All: Using Honeypots to Catch Adversarial Attacks on Neural NetworksCode0
Visual explanation of black-box model: Similarity Difference and Uniqueness (SIDU) methodCode0
Fast Adversarial CNN-based Perturbation Attack of No-Reference Image Quality MetricsCode0
Angelic Patches for Improving Third-Party Object Detector PerformanceCode0
Exploring the Vulnerability of Natural Language Processing Models via Universal Adversarial TextsCode0
Extending Adversarial Attacks to Produce Adversarial Class Probability DistributionsCode0
A New Ensemble Adversarial Attack Powered by Long-term Gradient MemoriesCode0
Fashion-Guided Adversarial Attack on Person SegmentationCode0
Fast Inference of Removal-Based Node InfluenceCode0
Explainable Graph Neural Networks Under FireCode0
An Empirical Investigation of Randomized Defenses against Adversarial AttacksCode0
Explaining Adversarial Robustness of Neural Networks from Clustering Effect PerspectiveCode0
Expanding Scope: Adapting English Adversarial Attacks to ChineseCode0
Explainable and Safe Reinforcement Learning for Autonomous Air MobilityCode0
Exact Adversarial Attack to Image Captioning via Structured Output Learning with Latent VariablesCode0
EvoBA: An Evolution Strategy as a Strong Baseline forBlack-Box Adversarial AttacksCode0
Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and ChallengesCode0
Exacerbating Algorithmic Bias through Fairness AttacksCode0
Excess Capacity and Backdoor PoisoningCode0
Exploiting vulnerabilities of deep neural networks for privacy protectionCode0
Physics-constrained Attack against Convolution-based Human Motion PredictionCode0
A Classification-Guided Approach for Adversarial Attacks against Neural Machine TranslationCode0
Evaluating and Understanding the Robustness of Adversarial Logit PairingCode0
Adversarial Attack Vulnerability of Medical Image Analysis Systems: Unexplored FactorsCode0
EvadeDroid: A Practical Evasion Attack on Machine Learning for Black-box Android Malware DetectionCode0
Show:102550
← PrevPage 22 of 73Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Xu et al.Attack: PGD2078.68Unverified
23-ensemble of multi-resolution self-ensemblesAttack: AutoAttack78.13Unverified
3TRADES-ANCRA/ResNet18Attack: AutoAttack59.7Unverified
4AdvTraining [madry2018]Attack: PGD2048.44Unverified
5TRADES [zhang2019b]Attack: PGD2045.9Unverified
6XU-NetRobust Accuracy1Unverified
#ModelMetricClaimedVerifiedStatus
13-ensemble of multi-resolution self-ensemblesAttack: AutoAttack51.28Unverified
2multi-resolution self-ensemblesAttack: AutoAttack47.85Unverified