membership-inference

[ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation" by Chongyu Fan*, Jiancheng Liu*, Yihua Zhang, Eric Wong, Dennis Wei, Sijia Liu

generative-model data-privacy diffusion machine-unlearning forgetting diffusion-models data-deletion membership-inference-attack unlearning membership-inference data-removal

Updated Feb 28, 2026
Python

OPTML-Group / Unlearn-Sparse

Star

[NeurIPS23 (Spotlight)] "Model Sparsity Can Simplify Machine Unlearning" by Jinghan Jia*, Jiancheng Liu*, Parikshit Ram, Yuguang Yao, Gaowen Liu, Yang Liu, Pranay Sharma, Sijia Liu

data-privacy machine-unlearning forgetting data-deletion membership-inference-attack unlearning membership-inference data-removal

Updated Jun 28, 2026
Python

lennart-finke / gpt-oss

Star

What does gpt-oss tell us about OpenAI's training data?

membership-inference open-weight gpt-oss

Updated Sep 19, 2025
Python

Koukyosyumei / Attack_SplitNN

Star

reveal the vulnerabilities of SplitNN

privacy attack notebook paper security-vulnerability leakage model-inversion model-inversion-attacks split-learning membership-inference-attack splitnn membership-inference attack-splitnn

Updated Jun 16, 2022
Python

ryuryukke / MINT

Star

[ICMLW 2026] The official repository for our paper, "Machine Text Detectors are Membership Inference Attacks"

nlp detection evaluation memorization ai-generated membership-inference-attacks membership-inference generated-text llms generated-text-detection ai-generated-text-detection

Updated Jul 4, 2026
Python

sabrinahaniff / genai-privacy-audit

Star

Exploring how GANs leak private training data through MIA, and whether DP can stop it

visualization python research ml generative-adversarial-network gans dp differential-privacy membership-inference-attack membership-inference generative-ai

Updated May 4, 2026
Python

gongzhimin / Copyright-Protection-Studies-in-Deep-Learning

Star

A repository about literature of copyright protection in deep learning.

deep-learning adversarial-attacks copyright-protection backdoor-attacks membership-inference ownership-verification

Updated Dec 22, 2023

Yaxin9Luo / LLMSurgeon

Star

(ACL 2026 Main) LLMSurgeon recovers the pretraining data mixture of any LLM from only its generated text — no weights, no training data. A calibrated domain classifier plus label-shift correction de-blurs biased predictions. Ships with LLMScan, a benchmark on 8 open-source LLMs.

data-provenance label-shift membership-inference large-language-models llm-analysis pretraining-data data-mixture acl2026

Updated May 29, 2026
Python

DeliciousBuding / DiffAudit-Research

Star

Reproducible research scaffolding for privacy-risk auditing of diffusion models.

python research reproducibility machine-learning-security diffusion-models membership-inference privacy-auditing

Updated Aug 11, 2026
Python

sabrinahaniff / membership-inference-attack

Star

Membership inference attack simulator: overfitting leaks training data, differential privacy defends against it

python machine-learning graph scikit-learn regularization differential-privacy overfitting membership-inference-attack membership-inference

Updated May 19, 2026
Python

rudrasingh-007 / Spectra

Star

An LLM Privacy Risk Evaluation Tool that probes AI models for PII generation risk, training data regurgitation, and membership inference signals.

python security machine-learning privacy gemini cybersecurity ai-safety red-teaming pii-detection streamlit membership-inference llm adversarial-prompting audit-tool

Updated May 11, 2026
Python

crayon-go / machine-unlearning-papers

Star

A continuously-updated catalog of machine unlearning papers with live citation counts.

Updated May 11, 2026

HailongHuPri / LTMI

Star

Unveiling Privacy Risks in the Long Tail: Membership Inference in Class Skewness

long-tail membership-inference

Updated Dec 10, 2025
Python

ShaistaShabbir-prog / ai-insights-suite-open-source

Star

🤖 AI Insights Suite — NLP tools for privacy, explainability and membership inference attacks

python nlp machine-learning privacy ai explainable-ai membership-inference

Updated Jul 3, 2026

boumezbeuraya / SecureMed-LLM-A-Privacy-Preserving1-Framework-for-Safeguarding-Clinical2-Language-Models

Star

SecureMed-LLM: A privacy-preserving framework for clinical report generation from chest X-rays, integrating Med-Guard anonymization, DP-SGD (ε=3.0), adversarial training, IDS-LLM validation, and ECIES/Curve25519 encryption. PeerJ Computer Science 2025.

Updated Jun 18, 2026
Python

Improve this page

Add a description, image, and links to the membership-inference topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the membership-inference topic, visit your repo's landing page and select "manage topics."

Learn more