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 801–825 of 1808 papers

TitleStatusHype
Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion—0
FlippedRAG: Black-Box Opinion Manipulation Adversarial Attacks to Retrieval-Augmented Generation Models—0
Analytically Tractable Hidden-States Inference in Bayesian Neural Networks—0
Adversarial Music: Real World Audio Adversary Against Wake-word Detection System—0
Adversarial Attack with Pattern Replacement—0
Headless Horseman: Adversarial Attacks on Transfer Learning Models—0
Defense Against Explanation Manipulation—0
Fooling Adversarial Training with Inducing Noise—0
Fooling Adversarial Training with Induction Noise—0
Defense against Adversarial Cloud Attack on Remote Sensing Salient Object Detection—0
Analysis of the vulnerability of machine learning regression models to adversarial attacks using data from 5G wireless networks—0
FoolSDEdit: Deceptively Steering Your Edits Towards Targeted Attribute-aware Distribution—0
Forbidden Facts: An Investigation of Competing Objectives in Llama-2—0
A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Meme Stock Prediction—0
An AI-Enabled Framework to Defend Ingenious MDT-based Attacks on the Emerging Zero Touch Cellular Networks—0
Adversarial Attack and Defense for LoRa Device Identification and Authentication via Deep Learning—0
Hear No Evil: Towards Adversarial Robustness of Automatic Speech Recognition via Multi-Task Learning—0
An Adversarial Attack via Feature Contributive Regions—0
Hardware Accelerator for Adversarial Attacks on Deep Learning Neural Networks—0
An Adversarial Attack Defending System for Securing In-Vehicle Networks—0
Post-train Black-box Defense via Bayesian Boundary Correction—0
Frequency-Tuned Universal Adversarial Attacks—0
Adversarial Attack Type I: Cheat Classifiers by Significant Changes—0
Harmonic Adversarial Attack Method—0
A Computationally Efficient Method for Defending Adversarial Deep Learning Attacks—0
Show:102550
← PrevPage 33 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