SOTAVerified

Adversarial Defense

Competitions with currently unpublished results:

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 403 papers

TitleStatusHype
Deep Adversarial Defense Against Multilevel-Lp Attacks—0
Shedding More Light on Robust Classifiers under the lens of Energy-based ModelsCode0
L_p-norm Distortion-Efficient Adversarial Attack—0
DiffuseDef: Improved Robustness to Adversarial Attacks via Iterative DenoisingCode0
Deciphering the Definition of Adversarial Robustness for post-hoc OOD DetectorsCode0
GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning—0
MaskPure: Improving Defense Against Text Adversaries with Stochastic PurificationCode0
Improving Adversarial Robustness via Decoupled Visual Representation MaskingCode0
MirrorCheck: Efficient Adversarial Defense for Vision-Language Models—0
Adversarial Evasion Attack Efficiency against Large Language Models—0
Talos: A More Effective and Efficient Adversarial Defense for GNN Models Based on the Global Homophily of Graphs—0
Multimodal Adversarial Defense for Vision-Language Models by Leveraging One-To-Many Relationships—0
Towards Unified Robustness Against Both Backdoor and Adversarial AttacksCode0
Large Language Model Sentinel: LLM Agent for Adversarial Purification—0
Robust width: A lightweight and certifiable adversarial defenseCode0
Adaptive Batch Normalization Networks for Adversarial Robustness—0
The Pitfalls and Promise of Conformal Inference Under Adversarial AttacksCode0
Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal PerspectiveCode0
Causal Perception Inspired Representation Learning for Trustworthy Image Quality Assessment—0
AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation—0
Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion ModelsCode1
Struggle with Adversarial Defense? Try Diffusion—0
Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks—0
Adversarial Attacks and Dimensionality in Text Classifiers—0
Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay—0
Ensemble Adversarial Defense via Integration of Multiple Dispersed Low Curvature Models—0
Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals—0
Adversarial Defense Teacher for Cross-Domain Object Detection under Poor Visibility Conditions—0
ADAPT to Robustify Prompt Tuning Vision TransformersCode0
Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSMCode0
Revisiting Adversarial Training under Long-Tailed DistributionsCode2
Adversarial Infrared Geometry: Using Geometry to Perform Adversarial Attack against Infrared Pedestrian Detectors—0
Enhancing the "Immunity" of Mixture-of-Experts Networks for Adversarial Defense—0
Enhancing Tracking Robustness with Auxiliary Adversarial Defense Networks—0
MGE: A Training-Free and Efficient Model Generation and Enhancement Scheme—0
Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off—0
A Simple and Yet Fairly Effective Defense for Graph Neural NetworksCode0
Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language ModelsCode2
Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness—0
Fast Adversarial Training against Textual Adversarial Attacks—0
AR-GAN: Generative Adversarial Network-Based Defense Method Against Adversarial Attacks on the Traffic Sign Classification System of Autonomous Vehicles—0
Adversarial Infrared Curves: An Attack on Infrared Pedestrian Detectors in the Physical World—0
Continual Adversarial DefenseCode0
Detection and Defense of Unlearnable ExamplesCode0
Robust MRI Reconstruction by Smoothed Unrolling (SMUG)Code0
Collapse-Aware Triplet Decoupling for Adversarially Robust Image RetrievalCode1
Defense Against Adversarial Attacks using Convolutional Auto-EncodersCode0
Efficient Key-Based Adversarial Defense for ImageNet by Using Pre-trained Model—0
Learn from the Past: A Proxy Guided Adversarial Defense Framework with Self Distillation RegularizationCode0
Provably Cost-Sensitive Adversarial Defense via Randomized SmoothingCode0
Show:102550
← PrevPage 2 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