Calibrating One-Round Membership Inference with Neighbors
cs.CR, cs.AI, cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
- Scalable Membership Inference Attacks via Quantile Regression
- Membership Inference Attacks From First Principles
- Extracting Training Data from Large Language Models
- RelaxLoss: Defending Membership Inference Attacks without Losing Utility
- Shadow-Free Membership Inference Attacks: Recommender Systems Are More Vulnerable Than You Thought
- CINIC-10 is not ImageNet or CIFAR-10
- DeepSeek-V3 Technical Report
- Toward Efficient Membership Inference Attacks against Federated Large Language Models: A Projection Residual Approach
- Cascading and Proxy Membership Inference Attacks
- Noisy Neighbors: Efficient membership inference attacks against LLMs
- How Well Can Differential Privacy Be Audited in One Run?
- l-Leaks: Membership Inference Attacks with Logits
- Membership Inference Attacks by Exploiting Loss Trajectory
- Auditing $f$-Differential Privacy in One Run
- Membership Inference Attacks against Language Models via Neighbourhood Comparison
- Semantic Membership Inference Attack against Large Language Models
- Learning Transferable Visual Models From Natural Language Supervision
- High-Resolution Image Synthesis with Latent Diffusion Models
- ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs