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 14761500 of 1808 papers

TitleStatusHype
Hard-label based Small Query Black-box Adversarial AttackCode0
Improving Sequence Modeling Ability of Recurrent Neural Networks via SememesCode0
Unpacking the Resilience of SNLI Contradiction Examples to AttacksCode0
A New Ensemble Adversarial Attack Powered by Long-term Gradient MemoriesCode0
ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object DetectorCode0
Harnessing the Vulnerability of Latent Layers in Adversarially Trained ModelsCode0
Enhancing Real-World Adversarial Patches through 3D Modeling of Complex Target ScenesCode0
Bridging the Performance Gap between FGSM and PGD Adversarial TrainingCode0
Towards Adaptive Meta-Gradient Adversarial Examples for Visual TrackingCode0
Adversarial Examples in Modern Machine Learning: A ReviewCode0
An Empirical Investigation of Randomized Defenses against Adversarial AttacksCode0
Trust Region Based Adversarial Attack on Neural NetworksCode0
Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face RecognitionCode0
Heuristic Black-box Adversarial Attacks on Video Recognition ModelsCode0
Towards Adversarial Patch Analysis and Certified Defense against Crowd CountingCode0
Enhancing Neural Models with Vulnerability via Adversarial AttackCode0
Towards adversarial robustness verification of no-reference image-and video-quality metricsCode0
Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion ReductionCode0
Hierarchical Perceptual Noise Injection for Social Media Fingerprint Privacy ProtectionCode0
High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image SynthesisCode0
Practical Relative Order Attack in Deep RankingCode0
An adversarial attack approach for eXplainable AI evaluation on deepfake detection modelsCode0
Sign-OPT: A Query-Efficient Hard-label Adversarial AttackCode0
Enhancing Adversarial Robustness with Conformal Prediction: A Framework for Guaranteed Model ReliabilityCode0
How Private Is Your RL Policy? An Inverse RL Based Analysis FrameworkCode0
Show:102550
← PrevPage 60 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