SOTAVerified

Inference Attack

Papers

Showing 176200 of 283 papers

TitleStatusHype
Quality Inference in Federated Learning with Secure Aggregation0
Tool Unlearning for Tool-Augmented LLMs0
Towards Black-Box Membership Inference Attack for Diffusion Models0
Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models0
Towards More Realistic Membership Inference Attacks on Large Diffusion Models0
Towards Reliable Empirical Machine Unlearning Evaluation: A Game-Theoretic View0
Quantifying the Privacy Risks of Learning High-Dimensional Graphical Models0
On the Impact of Uncertainty and Calibration on Likelihood-Ratio Membership Inference Attacks0
Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning0
Unlearning Clients, Features and Samples in Vertical Federated Learning0
Unveiling Client Privacy Leakage from Public Dataset Usage in Federated Distillation0
Unveiling Privacy Vulnerabilities: Investigating the Role of Structure in Graph Data0
Unveiling Structural Memorization: Structural Membership Inference Attack for Text-to-Image Diffusion Models0
Unveiling Synthetic Faces: How Synthetic Datasets Can Expose Real Identities0
User-Level Membership Inference Attack against Metric Embedding Learning0
VertexSerum: Poisoning Graph Neural Networks for Link Inference0
WaKA: Data Attribution using K-Nearest Neighbors and Membership Privacy Principles0
Membership Inference Attacks Against Temporally Correlated Data in Deep Reinforcement Learning0
Whispers of Data: Unveiling Label Distributions in Federated Learning Through Virtual Client Simulation0
White-box Inference Attacks against Centralized Machine Learning and Federated Learning0
White-box Membership Attack Against Machine Learning Based Retinopathy Classification0
Machine Unlearning for Uplink Interference Cancellation0
Machine unlearning via GAN0
Many-Shot Regurgitation (MSR) Prompting0
Against Membership Inference Attack: Pruning is All You Need0
Show:102550
← PrevPage 8 of 12Next →

No leaderboard results yet.