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 1–10 of 1808 papers

TitleStatusHype
3DGAA: Realistic and Robust 3D Gaussian-based Adversarial Attack for Autonomous Driving—0
VIP: Visual Information Protection through Adversarial Attacks on Vision-Language ModelsCode0
Identifying the Smallest Adversarial Load Perturbations that Render DC-OPF InfeasibleCode0
ScoreAdv: Score-based Targeted Generation of Natural Adversarial Examples via Diffusion ModelsCode1
3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage GenerationCode0
Robustness of Misinformation Classification Systems to Adversarial Examples Through BeamAttackCode0
Poster: Enhancing GNN Robustness for Network Intrusion Detection via Agent-based Analysis—0
DRO-Augment Framework: Robustness by Synergizing Wasserstein Distributionally Robust Optimization and Data Augmentation—0
Adversarial Attacks and Detection in Visual Place Recognition for Safer Robot NavigationCode1
Doppelganger Method: Breaking Role Consistency in LLM Agent via Prompt-based Transferable Adversarial Attack—0
Show:102550
← PrevPage 1 of 181Next →
All datasetsCIFAR-10CIFAR-100

Benchmark Results

#ModelMetricClaimedVerifiedStatus
13-ensemble of multi-resolution self-ensemblesAttack: AutoAttack51.28—Unverified
2multi-resolution self-ensemblesAttack: AutoAttack47.85—Unverified