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 126150 of 1808 papers

TitleStatusHype
Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking ModelsCode1
TSFool: Crafting Highly-Imperceptible Adversarial Time Series through Multi-Objective AttackCode1
Scattering Model Guided Adversarial Examples for SAR Target Recognition: Attack and DefenseCode1
Unrestricted Black-box Adversarial Attack Using GAN with Limited QueriesCode1
UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QACode1
MENLI: Robust Evaluation Metrics from Natural Language InferenceCode1
InvisibiliTee: Angle-agnostic Cloaking from Person-Tracking Systems with a TeeCode1
Defensive Distillation based Adversarial Attacks Mitigation Method for Channel Estimation using Deep Learning Models in Next-Generation Wireless NetworksCode1
LGV: Boosting Adversarial Example Transferability from Large Geometric VicinityCode1
SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation RobustnessCode1
Prior-Guided Adversarial Initialization for Fast Adversarial TrainingCode1
CARBEN: Composite Adversarial Robustness BenchmarkCode1
Perturbation Inactivation Based Adversarial Defense for Face RecognitionCode1
Frequency Domain Model Augmentation for Adversarial AttackCode1
BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean LabelCode1
Towards Adversarial Attack on Vision-Language Pre-training ModelsCode1
Boosting the Adversarial Transferability of Surrogate Models with Dark KnowledgeCode1
Adversarial Vulnerability of Randomized EnsemblesCode1
Proximal Splitting Adversarial Attacks for Semantic SegmentationCode1
NeuroUnlock: Unlocking the Architecture of Obfuscated Deep Neural NetworksCode1
On the Robustness of Safe Reinforcement Learning under Observational PerturbationsCode1
Transferable Adversarial Attack based on Integrated GradientsCode1
Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query AttacksCode1
Recipe2Vec: Multi-modal Recipe Representation Learning with Graph Neural NetworksCode1
Phrase-level Textual Adversarial Attack with Label PreservationCode1
Show:102550
← PrevPage 6 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