CIFAR-10
Emerging59papers using it
2,602HF downloads
0HF likes
2018first seen
CIFAR-10 is a dataset containing 60,000 32x32 color images across 10 different classes, commonly used to evaluate the performance of machine learning models, particularly in image classification tasks.
Papers using CIFAR-10 (59)
- Deep K-nn Defense Against Clean-label Data Poisoning AttacksProvable Defense Against Privacy Leakage In Federated Learning From Representation PerspectiveADS-C: Antidistillation Sampling for ClassificationToward a Generalized Defense Across Sparse, Continuous, and Structured Parameter AttacksReinforcement Learning Disrupts Gradient-Based Adversarial OptimizationCan Quantum Federated Learning Withstand Circuit-Level Backdoors?Res-MIA: A Training-Free Resolution-Based Membership Inference Attack on Federated Learning ModelsHardening Deep Neural Networks Via Adversarial Model CascadesSemantic Preserving Adversarial Attack Generation With Autoencoder And Genetic AlgorithmTEMPO-Diffusion: Temporally Exposed Malicious Poisoning of Diffusion ModelsParsimonious Black-box Adversarial Attacks Via Efficient Combinatorial OptimizationNonlinear Transformations Against Unlearnable DatasetsVFLIP: A Backdoor Defense For Vertical Federated Learning Via Identification And PurificationAdversarial Sparse Teacher: Defense Against Distillation-based Model Stealing Attacks Using Adversarial ExamplesHow Worst-case Are Adversarial Attacks? Linking Adversarial And Perturbation RobustnessDetection of Adversarial Examples Through Chaotic Features Extracted From Ordinal PatternsGeometrical Perturbations in Generative Models for Black-Box Adversarial AttackPubdef: Defending Against Transfer Attacks From Public ModelsCheckerboard: A Simple, Effective, Efficient and Learning-free Clean Label Backdoor Attack with Low Poisoning BudgetProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split LearningQShield: Securing Neural Networks Against Adversarial Attacks using Quantum CircuitsRPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset ImbalanceDCInject: Persistent Backdoor Attacks via Frequency Manipulation in Personal Federated LearningSecureSplit: Mitigating Backdoor Attacks in Split LearningEnhancing All-to-X Backdoor Attacks with Optimized Target Class MappingIlluminating the Black Box: Real-Time Monitoring of Backdoor Unlearning in CNNs via Explainable AIInjection, Attack and Erasure: Revocable Backdoor Attacks via Machine UnlearningA Versatile Framework for Designing Group-Sparse Adversarial AttacksHAMLOCK: HArdware-Model LOgically Combined attacKDefending Against Beta Poisoning Attacks in Machine Learning ModelsDASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial ExamplesDOPA: Stealthy and Generalizable Backdoor Attacks from a Single Client under Challenging Federated ConstraintsTED-LaST: Towards Robust Backdoor Defense Against Adaptive AttacksSmoothed Inference For Adversarially-trained ModelsA Little Is Enough: Circumventing Defenses For Distributed LearningRevisiting Personalized Federated Learning: Robustness Against Backdoor AttacksThere Are No Bit Parts For Sign Bits In Black-box AttacksAre Odds Really Odd? Bypassing Statistical Detection Of Adversarial ExamplesAdversarial Attack On Attackers: Post-process To Mitigate Black-box Score-based Query AttacksActive Learning Under Malicious Mislabeling And Poisoning AttacksMembership Inference Attack Using Self Influence FunctionsFedgt: Identification Of Malicious Clients In Federated Learning With Secure AggregationYour Out-of-distribution Detection Method Is Not Robust!Meta-learning The Search Distribution Of Black-box Random Search Based Adversarial AttacksAuxblocks: Defense Adversarial Example Via Auxiliary Blocks"what's In The Box?!": Deflecting Adversarial Attacks By Randomly Deploying Adversarially-disjoint ModelsProtecting Against Simultaneous Data Poisoning AttacksIncompatibility Clustering As A Defense Against Backdoor Poisoning AttacksUsing Anomaly Feature Vectors For Detecting, Classifying And Warning Of Outlier Adversarial ExamplesBeating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient DirectionsInvestigating The Adversarial Robustness Of Density Estimation Using The Probability Flow ODELuring Of Transferable Adversarial Perturbations In The Black-box ParadigmTheoretical Corrections And The Leveraging Of Reinforcement Learning To Enhance Triangle AttackTowards Understanding How Self-training Tolerates Data Backdoor PoisoningAccumulative Poisoning Attacks On Real-time DataDeviations In Representations Induced By Adversarial AttacksAdvancing Adversarial Robustness Through Adversarial Logit UpdateData-Efficient Backdoor AttacksTowards Adversarially Robust Continual Learning