Awesome Machine Unlearning (A Survey of Machine Unlearning)

A resource repository for machine unlearning in large language models

[NeurIPS D&B '25] The one-stop repository for LLM unlearning

A common framework enabling companies to work together to protect consumers' privacy and data rights.

Amazon S3 Find and Forget is a solution to handle data erasure requests from data lakes stored on Amazon S3, for example, pursuant to the European General Data Protection Regulation (GDPR)

Right to be forgotten - directory of direct links to delete your account from persian web services. دایرکتوری حق فراموش شدن سرویس های ایرانی

RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024

Project website, methods and graphics for the investigative project on the Right to be Forgotten

chrome-plugin افزونه کروم سرویس حق فراموش شدن

Data Privacy platform that helps create and manage DSR requests from the users

firefox plugin افزونه فایرفاکس سرویس حق فراموش شدن

A one-stop, multi-GPU framework for image unlearning in vision models. SUPREME is easily extensible with new datasets, model architectures, evaluation metrics, and unlearning methods.

A tool for purging messages from DM chats in Discord

“Right to be Forgotten” is a right to have private information removed from the internet search engine, database, websites or other public platforms.

Provable right-to-be-forgotten for AI agent memory. DPDP/GDPR Article 17 erasure across graph (Cognee), vector (pgvector), and inference log (TensorZero), with a signed deletion receipt a regulator can verify offline.

Docs: https://erasus.readthedocs.io/en/latest/ Forget data from any foundation model without retraining. Erasus surgically removes concepts, behaviors, or training samples from LLMs, VLMs, and Diffusion models using coreset selection. 90% less compute, certified removal, multimodal support.

Provable, crypto-shredded erasure on a tamper-evident ledger. Prove a person is deleted everywhere, while the audit trail stays intact.

Crypto-shredding + proof-of-deletion engine: per-record AES-256-GCM keys, envelope encryption, and a signed, tamper-evident, offline-verifiable Certificate of Erasure. Provable GDPR/HIPAA data erasure. Zero dependencies.

Verifiable cryptographic erasure for AI memory — a runnable proof-of-concept.