No article text was recorded for this version.
shadow model computational overhead
Version 2 of 2287 papers326 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Free Record-Level Privacy Risk Evaluation Through Artifact-Based Methods
- Blog: Noisy Neighbors: Efficient membership inference attacks against LLMs
- Blog: Bayesian Estimation of Differential Privacy
- Blog: Bayesian Estimation of Differential Privacy
- Blog: Free Record-Level Privacy Risk Evaluation Through Artifact-Based Methods
- Blog: Scalable Membership Inference Attacks via Quantile Regression
- Blog: Strong Membership Inference Attacks on Massive Datasets and (Moderately) Large Language Models
- Blog: Empirical Comparison of Membership Inference Attacks in Deep Transfer Learning
- Blog: Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack
- Blog: A General Framework for Auditing Differentially Private Machine Learning
- Blog: The Elusive Pursuit of Replicating PATE-GAN: Benchmarking, Auditing, Debugging
- Blog: Membership Inference Attacks as Privacy Tools: Reliability, Disparity and Ensemble
- Blog: Towards More Realistic Membership Inference Attacks on Large Diffusion Models
- Blog: Cascading and Proxy Membership Inference Attacks
- Blog: Information-Theoretic Membership Inference for Granular Quantification of Memorization
- Blog: Achilles' Heels: Vulnerable Record Identification in Synthetic Data Publishing
- Blog: Lost in the Averages: A New Specific Setup to Evaluate Membership Inference Attacks Against Machine Learning Models
- Blog: The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage
- Blog: Confidence Is All You Need for MI Attacks
- Blog: Beyond Membership: Limitations of Add/Remove Adjacency in Differential Privacy
- Blog: Arbitrary Decisions Are a Hidden Cost of Differentially Private Training
- Blog: Exploring the limits of strong membership inference attacks on large language models
- Blog: Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment Approach
- Blog: Auditing Preference-Based Post-Training of LLMs via Strong Membership Inference Attacks
- Blog: Order of Magnitude Speedups for LLM Membership Inference
- Blog: To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling
- Blog: Privacy Threats in Stable Diffusion Models
- Blog: Bayesian Estimation of Differential Privacy
- Blog: Why Train More? Effective and Efficient Membership Inference via Memorization
- Blog: Unleashing the Power of Randomization in Auditing Differentially Private ML
- Blog: Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
- Blog: Scalable Membership Inference Attacks via Quantile Regression
- Blog: Adversary Instantiation: Lower Bounds for Differentially Private Machine Learning
- Blog: Empirical Comparison of Membership Inference Attacks in Deep Transfer Learning
- Blog: Context-Aware Membership Inference Attacks against Pre-trained Large Language Models
- Blog: GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation
- Blog: Explaining the Model, Protecting Your Data: Revealing and Mitigating the Data Privacy Risks of Post-Hoc Model Explanations via Membership Inference
- Blog: Predicting and analyzing memorization within fine-tuned Large Language Models
- Blog: An Information Theorist's Tour of Differential Privacy
- Blog: Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study
- Blog: Auditing Empirical Privacy Protection of Private LLM Adaptations
- Blog: White-box Membership Inference Attacks against Diffusion Models
- Blog: Efficient Membership Inference Attacks by Bayesian Neural Network
- Blog: Privacy Auditing with One (1) Training Run
- Blog: Hyperparameters in Score-Based Membership Inference Attacks
- Blog: Attack-Aware Noise Calibration for Differential Privacy
- Blog: Measuring Déjà vu Memorization Efficiently
- Blog: Unintended Memorization in Large ASR Models, and How to Mitigate It
- Blog: Targeted Training Data Extraction—Neighborhood Comparison-Based Membership Inference Attacks in Large Language Models
- Blog: ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models
- Blog: Mnemonist: Locating Model Parameters that Memorize Training Examples
- Blog: Toward Efficient Membership Inference Attacks against Federated Large Language Models: A Projection Residual Approach
- Blog: TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models
- Blog: Automatic Calibration for Membership Inference Attack on Large Language Models
- Blog: Tight and Practical Privacy Auditing for Differentially Private In-Context Learning
- Blog: Differentially Private Nonparametric Hypothesis Testing
- Blog: TMI! Finetuned Models Leak Private Information from their Pretraining Data
- Blog: Sequentially Auditing Differential Privacy
- Blog: Auditing Black-Box Models for Indirect Influence
- Blog: Quantifying identifiability to choose and audit epsilon in differentially private deep learning
Showing 60 of 287 papers.
History & citation
Current · Permanent link
- Single Run Auditing for Differentially Private Models merged into this direction (83% overlap)
- Sample-Specific Calibration for Membership Inference Attacks merged into this direction (67% overlap)
- High-Precision Membership Inference for Privacy Auditing merged into this direction (50% overlap)
- high-confidence privacy auditing split from this direction (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_shadow_model_computational_overhead_78cd68f6,
title = {shadow model computational overhead},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/shadow-model-computational-overhead/rdr_78cd68f657bc413491bc30bd66711c04},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 2, frozen text):
@misc{lacuna_shadow_model_computational_overhead_78cd68f6_v2,
title = {shadow model computational overhead},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/shadow-model-computational-overhead/rdr_78cd68f657bc413491bc30bd66711c04/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-19},
}