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 851875 of 1808 papers

TitleStatusHype
Physical-World Optical Adversarial Attacks on 3D Face Recognition0
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 Robots0
Transferable Physical Attack against Object Detection with Separable Attention0
Sparse Adversarial Attack in Multi-agent Reinforcement Learning0
3D-VFD: A Victim-free Detector against 3D Adversarial Point Clouds0
Learn2Weight: Parameter Adaptation against Similar-domain Adversarial Attacks0
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 images0
Holistic Approach to Measure Sample-level Adversarial Vulnerability and its Utility in Building Trustworthy Systems0
Rethinking Classifier and Adversarial Attack0
CE-based white-box adversarial attacks will not work using super-fitting0
BERTops: Studying BERT Representations under a Topological LensCode0
Deep-Attack over the Deep Reinforcement Learning0
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 network0
Adversarial Fine-tune with Dynamically Regulated Adversary0
An Adversarial Attack Analysis on Malicious Advertisement URL Detection FrameworkCode0
Restricted Black-box Adversarial Attack Against DeepFake Face Swapping0
Boosting Adversarial Transferability of MLP-Mixer0
Self-recoverable Adversarial Examples: A New Effective Protection Mechanism in Social NetworksCode1
Mixed Strategies for Security Games with General Defending Requirements0
Show:102550
← PrevPage 35 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