SOTAVerified

Adversarial Defense

Competitions with currently unpublished results:

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 201–250 of 403 papers

TitleStatusHype
CAAD 2018: Generating Transferable Adversarial ExamplesCode0
All You Need is RAW: Defending Against Adversarial Attacks with Camera Image PipelinesCode0
Towards Effective and Efficient Adversarial Defense with Diffusion Models for Robust Visual TrackingCode0
Towards Unified Robustness Against Both Backdoor and Adversarial AttacksCode0
GraphDefense: Towards Robust Graph Convolutional NetworksCode0
Accidental Misalignment: Fine-Tuning Language Models Induces Unexpected VulnerabilityCode0
Defending against adversarial attacks on medical imaging AI system, classification or detection?Code0
PPD: Permutation Phase Defense Against Adversarial Examples in Deep LearningCode0
Defending Against Universal Attacks Through Selective Feature RegenerationCode0
Privacy Risks of Securing Machine Learning Models against Adversarial ExamplesCode0
Defending against black-box adversarial attacks with gradient-free trained sign activation neural networksCode0
Provably Cost-Sensitive Adversarial Defense via Randomized SmoothingCode0
Erasing, Transforming, and Noising Defense Network for Occluded Person Re-IdentificationCode0
Defending Substitution-Based Profile Pollution Attacks on Sequential RecommendersCode0
Defense against Adversarial Attacks Using High-Level Representation Guided DenoiserCode0
Error Correcting Output Codes Improve Probability Estimation and Adversarial Robustness of Deep Neural NetworksCode0
RAIN: A Simple Approach for Robust and Accurate Image Classification NetworksCode0
Defense Against Adversarial Attacks using Convolutional Auto-EncodersCode0
A Simple and Yet Fairly Effective Defense for Graph Neural NetworksCode0
Struggle with Adversarial Defense? Try Diffusion—0
OTAD: An Optimal Transport-Induced Robust Model for Agnostic Adversarial Attack—0
A Comprehensive Evaluation Framework for Deep Model Robustness—0
Active Adversarial Noise Suppression for Image Forgery Localization—0
Adaptive Batch Normalization Networks for Adversarial Robustness—0
Adaptive Feature Alignment for Adversarial Training—0
AdPO: Enhancing the Adversarial Robustness of Large Vision-Language Models with Preference Optimization—0
Adversarial Amendment is the Only Force Capable of Transforming an Enemy into a Friend—0
Adversarial Attacks and Defences for Skin Cancer Classification—0
Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Survey—0
Adversarial Attacks and Dimensionality in Text Classifiers—0
Adversarial-Aware Deep Learning System based on a Secondary Classical Machine Learning Verification Approach—0
Adversarial Defense based on Structure-to-Signal Autoencoders—0
Adversarial Defense by Latent Style Transformations—0
Adversarial defense for automatic speaker verification by cascaded self-supervised learning models—0
Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning—0
Adversarial defense for deep speaker recognition using hybrid adversarial training—0
Adversarial Defense Teacher for Cross-Domain Object Detection under Poor Visibility Conditions—0
Adversarial Defense Through Network Profiling Based Path Extraction—0
Adversarial Defense via Image Denoising with Chaotic Encryption—0
Adversarial Defense via Local Flatness Regularization—0
Adversarial Defense via Neural Oscillation inspired Gradient Masking—0
Adversarial Evasion Attack Efficiency against Large Language Models—0
Adversarial Examples for Electrocardiograms—0
Adversarial Infrared Curves: An Attack on Infrared Pedestrian Detectors in the Physical World—0
Adversarial Infrared Geometry: Using Geometry to Perform Adversarial Attack against Infrared Pedestrian Detectors—0
Adversarially Robust AI-Generated Image Detection for Free: An Information Theoretic Perspective—0
Adversarial Attacks and Defenses: An Interpretation Perspective—0
Adversarial Masked Autoencoder Purifier with Defense Transferability—0
Adversarial Robustness through Local Linearization—0
Adversarial Transferability in Deep Denoising Models: Theoretical Insights and Robustness Enhancement via Out-of-Distribution Typical Set Sampling—0
Show:102550
← PrevPage 5 of 9Next →
All datasetsCIFAR-10ImageNet (non-targeted PGD, max perturbation=4)ImageNetImageNet (targeted PGD, max perturbation=16)MNISTCAAD 2018miniImageNet

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1WRN-28-10Accuracy90.03—Unverified
2Diffusion ClassifierAccuracy89.85—Unverified
3Stochastic-LWTA/PGD/WideResNet-34-10Accuracy84.3—Unverified
4Ours (Stochastic-LWTA/PGD/WideResNet-34-5)Accuracy83.4—Unverified
5Ours (Stochastic-LWTA/PGD/WideResNet-34-1)Accuracy81.87—Unverified
6ResNet18 (TRADES-ANCRA/PGD-40)Accuracy81.7—Unverified
7Stochastic-LWTA/PGD/WideResNet-34-5Attack: AutoAttack81.22—Unverified
8PCL (against PGD, white box)Accuracy46.7—Unverified
#ModelMetricClaimedVerifiedStatus
1SAT-EfficientNet-L1Accuracy58.6—Unverified
2LLR-ResNet-152Accuracy47—Unverified
3ResNet-152 free-m=4Accuracy36—Unverified
4ResNet-101 free-m=4Accuracy34.3—Unverified
5ResNet-50 free-m=4Accuracy31.8—Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet101Accuracy99.8—Unverified
2InceptionV3Accuracy98.6—Unverified
3Feature DenoisingAccuracy49.5—Unverified
#ModelMetricClaimedVerifiedStatus
1ResNet-152 DenoiseAccuracy42.8—Unverified
2ResNeXt-101 DenoiseAllAccuracy40.4—Unverified
3ResNet-152Accuracy39—Unverified
#ModelMetricClaimedVerifiedStatus
1Defense GANAccuracy0.85—Unverified
2PuVAEAccuracy0.81—Unverified
#ModelMetricClaimedVerifiedStatus
1Feature DenoisingAccuracy50.6—Unverified
#ModelMetricClaimedVerifiedStatus
1Auto Encoder-Block Switching defense with GradCAMAccuracy 88.54—Unverified