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 926–950 of 1808 papers

TitleStatusHype
Pixel is All You Need: Adversarial Trajectory-Ensemble Active Learning for Salient Object Detection—0
General Adversarial Defense Against Black-box Attacks via Pixel Level and Feature Level Distribution Alignments—0
Understanding and Combating Robust Overfitting via Input Loss Landscape Analysis and RegularizationCode0
Targeted Adversarial Attacks against Neural Network Trajectory Predictors—0
Pareto Regret Analyses in Multi-objective Multi-armed Bandit—0
AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classification—0
Data Poisoning Attack Aiming the Vulnerability of Continual Learning—0
Foiling Explanations in Deep Neural NetworksCode0
Explainable and Safe Reinforcement Learning for Autonomous Air MobilityCode0
Benchmarking Adversarially Robust Quantum Machine Learning at Scale—0
PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples—0
Person Text-Image Matching via Text-Feature Interpretability Embedding and External Attack Node ImplantationCode0
Universal Distributional Decision-based Black-box Adversarial Attack with Reinforcement Learning—0
Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation—0
Generating Textual Adversaries with Minimal PerturbationCode0
Robust Smart Home Face Recognition under Starving Federated DataCode0
Contrastive Weighted Learning for Near-Infrared Gaze Estimation—0
Logits are predictive of network typeCode0
Symmetric Saliency-based Adversarial Attack To Speaker Identification—0
Improving the Transferability of Adversarial Attacks on Face Recognition with Beneficial Perturbation Feature Augmentation—0
TASA: Deceiving Question Answering Models by Twin Answer Sentences AttackCode0
LP-BFGS attack: An adversarial attack based on the Hessian with limited pixelsCode0
A White-Box Adversarial Attack Against a Digital Twin—0
TAPE: Assessing Few-shot Russian Language UnderstandingCode0
Similarity of Neural Architectures using Adversarial Attack Transferability—0
Show:102550
← PrevPage 38 of 73Next →
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