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 451–475 of 1808 papers

TitleStatusHype
RetouchUAA: Unconstrained Adversarial Attack via Image Retouching—0
Adversarial Purification of Information MaskingCode0
Trainwreck: A damaging adversarial attack on image classifiersCode0
When Side-Channel Attacks Break the Black-Box Property of Embedded Artificial Intelligence—0
AdvGen: Physical Adversarial Attack on Face Presentation Attack Detection Systems—0
Generating Valid and Natural Adversarial Examples with Large Language Models—0
Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts—0
DA^3: A Distribution-Aware Adversarial Attack against Language Models—0
An Extensive Study on Adversarial Attack against Pre-trained Models of CodeCode1
Learning Globally Optimized Language Structure via Adversarial Training—0
Robust Text Classification: Analyzing Prototype-Based NetworksCode0
Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and FlatnessCode0
Resilient and constrained consensus against adversarial attacks: A distributed MPC framework—0
Robust Adversarial Attacks Detection for Deep Learning based Relative Pose Estimation for Space Rendezvous—0
ABIGX: A Unified Framework for eXplainable Fault Detection and Classification—0
Army of Thieves: Enhancing Black-Box Model Extraction via Ensemble based sample selectionCode0
Optimal Cost Constrained Adversarial Attacks For Multiple Agent Systems—0
LFAA: Crafting Transferable Targeted Adversarial Examples with Low-Frequency Perturbations—0
Amoeba: Circumventing ML-supported Network Censorship via Adversarial Reinforcement LearningCode0
Differentially Private Reward Estimation with Preference Feedback—0
Boosting Decision-Based Black-Box Adversarial Attack with Gradient Priors—0
Adversarial sample generation and training using geometric masks for accurate and resilient license plate character recognitionCode0
Semantic-Aware Adversarial Training for Reliable Deep Hashing RetrievalCode0
AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language ModelsCode1
Imperceptible CMOS camera dazzle for adversarial attacks on deep neural networks—0
Show:102550
← PrevPage 19 of 73Next →
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