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 1251–1300 of 1808 papers

TitleStatusHype
Deep Feature Space Trojan Attack of Neural Networks by Controlled DetoxificationCode1
Variational Quantum Cloning: Improving Practicality for Quantum Cryptanalysis—0
Exploiting Vulnerability of Pooling in Convolutional Neural Networks by Strict Layer-Output Manipulation for Adversarial Attacks—0
Blurring Fools the Network -- Adversarial Attacks by Feature Peak Suppression and Gaussian Blurring—0
Efficient Training of Robust Decision Trees Against Adversarial ExamplesCode1
A Hierarchical Feature Constraint to Camouflage Medical Adversarial AttacksCode0
Exacerbating Algorithmic Bias through Fairness AttacksCode0
A Distributed Black-Box Adversarial Attack Based on Multi-Group Particle Swarm OptimizationCode0
Disentangled Information BottleneckCode1
Blindfolded Attackers Still Threatening: Strict Black-Box Adversarial Attacks on Graphs—0
Attack Agnostic Detection of Adversarial Examples via Random Subspace Analysis—0
Composite Adversarial AttacksCode1
SPAA: Stealthy Projector-based Adversarial Attacks on Deep Image ClassifiersCode1
Geometric Adversarial Attacks and Defenses on 3D Point CloudsCode1
Generating Out of Distribution Adversarial Attack using Latent Space Poisoning—0
Using Feature Alignment Can Improve Clean Average Precision and Adversarial Robustness in Object DetectionCode1
Towards Natural Robustness Against Adversarial Examples—0
FenceBox: A Platform for Defeating Adversarial Examples with Data Augmentation TechniquesCode0
Channel Effects on Surrogate Models of Adversarial Attacks against Wireless Signal Classifiers—0
Enhancing Neural Models with Vulnerability via Adversarial AttackCode0
Contrastive Zero-Shot Learning for Cross-Domain Slot Filling with Adversarial Attack—0
Adversarial Attacks on Deep Graph Matching—0
Adversarial Learning for Robust Deep ClusteringCode1
Just One Moment: Structural Vulnerability of Deep Action Recognition against One Frame Attack—0
Guided Adversarial Attack for Evaluating and Enhancing Adversarial DefensesCode1
A Targeted Universal Attack on Graph Convolutional NetworkCode0
FaceGuard: A Self-Supervised Defense Against Adversarial Face Images—0
NaturalAE: Natural and Robust Physical Adversarial Examples for Object Detectors—0
Probing Model Signal-Awareness via Prediction-Preserving Input Minimization—0
Adversarial Attack on Facial Recognition using Visible Light—0
SurFree: a fast surrogate-free black-box attackCode1
Augmented Lagrangian Adversarial AttacksCode1
A Sweet Rabbit Hole by DARCY: Using Honeypots to Detect Universal Trigger's Adversarial Attacks—0
Multi-Task Adversarial Attack—0
Adversarial Profiles: Detecting Out-Distribution & Adversarial Samples in Pre-trained CNNs—0
FoolHD: Fooling speaker identification by Highly imperceptible adversarial DisturbancesCode1
Combining GANs and AutoEncoders for Efficient Anomaly DetectionCode1
Dynamic backdoor attacks against federated learning—0
Fooling the primate brain with minimal, targeted image manipulation—0
Efficient and Transferable Adversarial Examples from Bayesian Neural NetworksCode0
Bridging the Performance Gap between FGSM and PGD Adversarial TrainingCode0
Single-Node Attacks for Fooling Graph Neural NetworksCode1
Dynamically Sampled Nonlocal Gradients for Stronger Adversarial Attacks—0
Defense-friendly Images in Adversarial Attacks: Dataset and Metrics for Perturbation DifficultyCode0
Deep-Dup: An Adversarial Weight Duplication Attack Framework to Crush Deep Neural Network in Multi-Tenant FPGACode0
Detecting Word Sense Disambiguation Biases in Machine Translation for Model-Agnostic Adversarial AttacksCode0
Second-Order NLP Adversarial Examples—0
TextAttack: Lessons learned in designing Python frameworks for NLP—0
Generalization to Mitigate Synonym Substitution Attacks—0
Utilizing Multimodal Feature Consistency to Detect Adversarial Examples on Clinical Summaries—0
Show:102550
← PrevPage 26 of 37Next →
All datasetsCIFAR-10CIFAR-100

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Xu et al.Attack: PGD2078.68—Unverified
23-ensemble of multi-resolution self-ensemblesAttack: AutoAttack78.13—Unverified
3TRADES-ANCRA/ResNet18Attack: AutoAttack59.7—Unverified
4AdvTraining [madry2018]Attack: PGD2048.44—Unverified
5TRADES [zhang2019b]Attack: PGD2045.9—Unverified
6XU-NetRobust Accuracy1—Unverified
#ModelMetricClaimedVerifiedStatus
13-ensemble of multi-resolution self-ensemblesAttack: AutoAttack51.28—Unverified
2multi-resolution self-ensemblesAttack: AutoAttack47.85—Unverified