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

Showing 14761500 of 1808 papers

TitleStatusHype
BankTweak: Adversarial Attack against Multi-Object Trackers by Manipulating Feature Banks0
Aug-ILA: More Transferable Intermediate Level Attacks with Augmented References0
CE-based white-box adversarial attacks will not work using super-fitting0
Audio Adversarial Examples: Attacks Using Vocal Masks0
BB-Patch: BlackBox Adversarial Patch-Attack using Zeroth-Order Optimization0
Seeing is Deceiving: Exploitation of Visual Pathways in Multi-Modal Language Models0
Benchmarking Adversarially Robust Quantum Machine Learning at Scale0
Benchmarking Adversarial Robustness0
Benchmarking Adversarial Robustness of Image Shadow Removal with Shadow-adaptive Attacks0
Attribution for Enhanced Explanation with Transferable Adversarial eXploration0
Benchmarking the Physical-world Adversarial Robustness of Vehicle Detection0
Benign Adversarial Attack: Tricking Models for Goodness0
Attribution-driven Causal Analysis for Detection of Adversarial Examples0
Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack0
Best Practices for Noise-Based Augmentation to Improve the Performance of Deployable Speech-Based Emotion Recognition Systems0
Attribute-Guided Encryption with Facial Texture Masking0
Seeking Flat Minima over Diverse Surrogates for Improved Adversarial Transferability: A Theoretical Framework and Algorithmic Instantiation0
Beyond Classification: Evaluating Diffusion Denoised Smoothing for Security-Utility Trade off0
Beyond Dropout: Robust Convolutional Neural Networks Based on Local Feature Masking0
SAM Meets UAP: Attacking Segment Anything Model With Universal Adversarial Perturbation0
Adversarial Attacks in Sound Event Classification0
Beyond Score Changes: Adversarial Attack on No-Reference Image Quality Assessment from Two Perspectives0
Self adversarial attack as an augmentation method for immunohistochemical stainings0
BiasAdv: Bias-Adversarial Augmentation for Model Debiasing0
Bias Field Poses a Threat to DNN-based X-Ray Recognition0
Show:102550
← PrevPage 60 of 73Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Xu et al.Attack: PGD2078.68Unverified
23-ensemble of multi-resolution self-ensemblesAttack: AutoAttack78.13Unverified
3TRADES-ANCRA/ResNet18Attack: AutoAttack59.7Unverified
4AdvTraining [madry2018]Attack: PGD2048.44Unverified
5TRADES [zhang2019b]Attack: PGD2045.9Unverified
6XU-NetRobust Accuracy1Unverified
#ModelMetricClaimedVerifiedStatus
13-ensemble of multi-resolution self-ensemblesAttack: AutoAttack51.28Unverified
2multi-resolution self-ensemblesAttack: AutoAttack47.85Unverified