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 576–600 of 1808 papers

TitleStatusHype
KNOW How to Make Up Your Mind! Adversarially Detecting and Alleviating Inconsistencies in Natural Language ExplanationsCode0
Adversary for Social Good: Leveraging Adversarial Attacks to Protect Personal Attribute Privacy—0
Adversarial Attack Based on Prediction-Correction—0
Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Search—0
Adversarial-Aware Deep Learning System based on a Secondary Classical Machine Learning Verification Approach—0
Graph-based methods coupled with specific distributional distances for adversarial attack detectionCode0
From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation FrameworkCode0
Adversarial Attack On Yolov5 For Traffic And Road Sign DetectionCode1
Modeling Adversarial Attack on Pre-trained Language Models as Sequential Decision MakingCode0
PEARL: Preprocessing Enhanced Adversarial Robust Learning of Image Deraining for Semantic Segmentation—0
Another Dead End for Morphological Tags? Perturbed Inputs and ParsingCode0
Enhancing Accuracy and Robustness through Adversarial Training in Class Incremental Continual Learning—0
Attribute-Guided Encryption with Facial Texture Masking—0
Latent Magic: An Investigation into Adversarial Examples Crafted in the Semantic Latent Space—0
Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial AttacksCode1
Are Your Explanations Reliable? Investigating the Stability of LIME in Explaining Text Classifiers by Marrying XAI and Adversarial AttackCode0
Dynamic Transformers Provide a False Sense of EfficiencyCode0
Spatial-Frequency Discriminability for Revealing Adversarial PerturbationsCode0
Adversarial Amendment is the Only Force Capable of Transforming an Enemy into a Friend—0
Content-based Unrestricted Adversarial Attack—0
Iterative Adversarial Attack on Image-guided Story Ending Generation—0
Attacking Perceptual Similarity Metrics—0
Diffusion Models for Imperceptible and Transferable Adversarial AttackCode2
A Black-Box Attack on Code Models via Representation Nearest Neighbor Search—0
The Best Defense is Attack: Repairing Semantics in Textual Adversarial Examples—0
Show:102550
← PrevPage 24 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