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 13011325 of 1808 papers

TitleStatusHype
Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence0
Tracking the Copyright of Large Vision-Language Models through Parameter Learning Adversarial Images0
Wavelets Beat Monkeys at Adversarial Robustness0
Weighted-Sampling Audio Adversarial Example Attack0
Query-Efficient Black-Box Attack by Active Learning0
Query-Efficient Hard-Label Black-Box Attack against Vision Transformers0
Data Poisoning Attack Aiming the Vulnerability of Continual Learning0
Query-Efficient Video Adversarial Attack with Stylized Logo0
Query-Free Adversarial Transfer via Undertrained Surrogates0
Blindfolded Attackers Still Threatening: Strict Black-Box Adversarial Attacks on Graphs0
RAF: Recursive Adversarial Attacks on Face Recognition Using Extremely Limited Queries0
Adversarial Data Encryption0
Attack Agnostic Detection of Adversarial Examples via Random Subspace Analysis0
Weight Map Layer for Noise and Adversarial Attack Robustness0
Adversarial Color Projection: A Projector-based Physical Attack to DNNs0
RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors0
Adversarial Client Detection via Non-parametric Subspace Monitoring in the Internet of Federated Things0
Adversarial Body Shape Search for Legged Robots0
Adversarial-Aware Deep Learning System based on a Secondary Classical Machine Learning Verification Approach0
The Best Defense is Attack: Repairing Semantics in Textual Adversarial Examples0
TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentation0
Realistic Scatterer Based Adversarial Attacks on SAR Image Classifiers0
What Machines See Is Not What They Get: Fooling Scene Text Recognition Models With Adversarial Text Images0
Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks0
Real-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition Systems0
Show:102550
← PrevPage 53 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