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 101125 of 1808 papers

TitleStatusHype
Adversarial Attack on Large Scale GraphCode1
CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating DeepfakesCode1
GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation ModelsCode1
Adversarial Vulnerabilities in Large Language Models for Time Series ForecastingCode1
Adversarial Attack On Yolov5 For Traffic And Road Sign DetectionCode1
AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing FlowsCode1
Attacking Video Recognition Models with Bullet-Screen CommentsCode1
Cooling-Shrinking Attack: Blinding the Tracker with Imperceptible NoisesCode1
Adv-Makeup: A New Imperceptible and Transferable Attack on Face RecognitionCode1
Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-ArtCode1
AGKD-BML: Defense Against Adversarial Attack by Attention Guided Knowledge Distillation and Bi-directional Metric LearningCode1
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language ModelsCode1
3D Adversarial Attacks Beyond Point CloudCode1
An integrated Auto Encoder-Block Switching defense approach to prevent adversarial attacksCode1
Attacking Recommender Systems with Augmented User ProfilesCode1
Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box FrameworkCode1
AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language ModelsCode1
Adversarial Attacks and Detection in Visual Place Recognition for Safer Robot NavigationCode1
Adversarial Attacks on ML Defense Models CompetitionCode1
Differentiable Language Model Adversarial Attacks on Categorical Sequence ClassifiersCode1
An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat LandscapeCode1
Discrete Point-wise Attack Is Not Enough: Generalized Manifold Adversarial Attack for Face RecognitionCode1
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted AttackCode1
An Extensive Study on Adversarial Attack against Pre-trained Models of CodeCode1
A Review of Adversarial Attack and Defense for Classification MethodsCode1
Show:102550
← PrevPage 5 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