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 101125 of 1808 papers

TitleStatusHype
Adversarial Attack on Large Scale GraphCode1
Adversarial Attacks on ML Defense Models CompetitionCode1
GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation ModelsCode1
Boosting the Transferability of Video Adversarial Examples via Temporal TranslationCode1
Adversarial Attack On Yolov5 For Traffic And Road Sign DetectionCode1
Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack FrameworkCode1
Adversarial Training for Free!Code1
Certifying LLM Safety against Adversarial PromptingCode1
On the Multi-modal Vulnerability of Diffusion ModelsCode1
Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-ArtCode1
Contextualized Perturbation for Textual Adversarial AttackCode1
Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Speech Foundation ModelsCode1
3D Adversarial Attacks Beyond Point CloudCode1
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasksCode1
Deep Variational Information BottleneckCode1
Adversarial Vulnerabilities in Large Language Models for Time Series ForecastingCode1
Adv-Makeup: A New Imperceptible and Transferable Attack on Face RecognitionCode1
Adversarial Attacks and Detection in Visual Place Recognition for Safer Robot NavigationCode1
DifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-DomainCode1
An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat LandscapeCode1
Differentiable Language Model Adversarial Attacks on Categorical Sequence ClassifiersCode1
Adversarial Ranking Attack and DefenseCode1
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted AttackCode1
Disentangled Information BottleneckCode1
Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition ModelCode1
Show:102550
← PrevPage 5 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