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 851–900 of 1808 papers

TitleStatusHype
Physical-World Optical Adversarial Attacks on 3D Face Recognition—0
Recipe2Vec: Multi-modal Recipe Representation Learning with Graph Neural NetworksCode1
Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query AttacksCode1
Phrase-level Textual Adversarial Attack with Label PreservationCode1
Adversarial Body Shape Search for Legged Robots—0
Transferable Physical Attack against Object Detection with Separable Attention—0
Sparse Adversarial Attack in Multi-agent Reinforcement Learning—0
3D-VFD: A Victim-free Detector against 3D Adversarial Point Clouds—0
Learn2Weight: Parameter Adaptation against Similar-domain Adversarial Attacks—0
MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin StatisticCode1
Btech thesis report on adversarial attack detection and purification of adverserially attacked images—0
Holistic Approach to Measure Sample-level Adversarial Vulnerability and its Utility in Building Trustworthy Systems—0
Rethinking Classifier and Adversarial Attack—0
CE-based white-box adversarial attacks will not work using super-fitting—0
BERTops: Studying BERT Representations under a Topological LensCode0
Deep-Attack over the Deep Reinforcement Learning—0
Uncertainty Estimation of Transformer Predictions for Misclassification DetectionCode0
A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock PredictionsCode1
Adversarial attacks on an optical neural network—0
Adversarial Fine-tune with Dynamically Regulated Adversary—0
An Adversarial Attack Analysis on Malicious Advertisement URL Detection FrameworkCode0
Boosting Adversarial Transferability of MLP-Mixer—0
Restricted Black-box Adversarial Attack Against DeepFake Face Swapping—0
Self-recoverable Adversarial Examples: A New Effective Protection Mechanism in Social NetworksCode1
Mixed Strategies for Security Games with General Defending Requirements—0
Improving Deep Learning Model Robustness Against Adversarial Attack by Increasing the Network Capacity—0
Smart App Attack: Hacking Deep Learning Models in Android AppsCode1
Enhancing the Transferability via Feature-Momentum Adversarial Attack—0
How Sampling Impacts the Robustness of Stochastic Neural Networks—0
A Mask-Based Adversarial Defense Scheme—0
Testing robustness of predictions of trained classifiers against naturally occurring perturbations—0
Metamorphic Testing-based Adversarial Attack to Fool Deepfake Detectors—0
CgAT: Center-Guided Adversarial Training for Deep Hashing-Based RetrievalCode1
UNBUS: Uncertainty-aware Deep Botnet Detection System in Presence of Perturbed Samples—0
Residue-Based Natural Language Adversarial Attack DetectionCode0
Homomorphic Encryption and Federated Learning based Privacy-Preserving CNN Training: COVID-19 Detection Use-Case—0
From Environmental Sound Representation to Robustness of 2D CNN Models Against Adversarial Attacks—0
Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization—0
Hear No Evil: Towards Adversarial Robustness of Automatic Speech Recognition via Multi-Task Learning—0
SecureSense: Defending Adversarial Attack for Secure Device-Free Human Activity Recognition—0
Adversarial Neon Beam: A Light-based Physical Attack to DNNs—0
Fusing Event-based and RGB camera for Robust Object Detection in Adverse ConditionsCode1
StyleFool: Fooling Video Classification Systems via Style TransferCode1
Exploring Frequency Adversarial Attacks for Face Forgery Detection—0
Zero-Query Transfer Attacks on Context-Aware Object Detectors—0
Boosting Black-Box Adversarial Attacks with Meta Learning—0
Text Adversarial Purification as Defense against Adversarial Attacks—0
A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologies—0
Enhancing Transferability of Adversarial Examples with Spatial Momentum—0
A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical FlowCode1
Show:102550
← PrevPage 18 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