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 15511575 of 1808 papers

TitleStatusHype
AICAttack: Adversarial Image Captioning Attack with Attention-Based OptimizationCode0
Improving Transferability of Adversarial Examples with Input DiversityCode0
Hidden Activations Are Not Enough: A General Approach to Neural Network PredictionsCode0
Query-efficient Meta Attack to Deep Neural NetworksCode0
A Hierarchical Feature Constraint to Camouflage Medical Adversarial AttacksCode0
A Game-Based Approximate Verification of Deep Neural Networks with Provable GuaranteesCode0
A Frank-Wolfe Framework for Efficient and Effective Adversarial AttacksCode0
Sparse and Imperceptible Adversarial Attack via a Homotopy AlgorithmCode0
Enhancing Adversarial Attacks: The Similar Target MethodCode0
Injecting and removing malignant features in mammography with CycleGAN: Investigation of an automated adversarial attack using neural networksCode0
Accuracy of TextFooler black box adversarial attacks on 01 loss sign activation neural network ensembleCode0
Random Transformation of Image Brightness for Adversarial AttackCode0
Boosting Adversarial Attacks with MomentumCode0
SPARK: Spatial-aware Online Incremental Attack Against Visual TrackingCode0
Block-Sparse Adversarial Attack to Fool Transformer-Based Text ClassifiersCode0
InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language ModelsCode0
Black-Box Adversarial Attack with Transferable Model-based EmbeddingCode0
Black-box Adversarial Attacks on Network-wide Multi-step Traffic State Prediction ModelsCode0
Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic GraphsCode0
READ: Improving Relation Extraction from an ADversarial PerspectiveCode0
Dynamics-aware Adversarial Attack of Adaptive Neural NetworksCode0
AdvPC: Transferable Adversarial Perturbations on 3D Point CloudsCode0
Real-Time Adversarial AttacksCode0
AdvHat: Real-world adversarial attack on ArcFace Face ID systemCode0
Visual explanation of black-box model: Similarity Difference and Uniqueness (SIDU) methodCode0
Show:102550
← PrevPage 63 of 73Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet20Test Accuracy89.9589.95(1)Community Verified
2Xu et al.Attack: PGD2078.68Unverified
33-ensemble of multi-resolution self-ensemblesAttack: AutoAttack78.13Unverified
4TRADES-ANCRA/ResNet18Attack: AutoAttack59.7Unverified
5AdvTraining [madry2018]Attack: PGD2048.44Unverified
6TRADES [zhang2019b]Attack: PGD2045.9Unverified
7XU-NetRobust Accuracy1Unverified
#ModelMetricClaimedVerifiedStatus
13-ensemble of multi-resolution self-ensemblesAttack: AutoAttack51.28Unverified
2multi-resolution self-ensemblesAttack: AutoAttack47.85Unverified