A library for mechanistic interpretability of GPT-style language models

Stream processing pipeline from Finnhub websocket using Spark, Kafka, Kubernetes and more

Training Sparse Autoencoders on Language Models

A Python package to scrub PII

Example projects using the AWS CDK

🌲 Code for our EMNLP 2023 paper - 🎄 "Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models"

A survey of privacy problems in Large Language Models (LLMs). Contains summary of the corresponding paper along with relevant code

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

Must-read Papers on Knowledge Editing for Large Language Models.

Machine Learning Interviews from FAANG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.

The code for "Improved Deep Leakage from Gradients" (iDLG).

Deep Leakage from Gradients(DLG) and Improved Deep Leakage from Gradeints(iDLG) jupyter notebook

[NeurIPS 2019] Deep Leakage From Gradients

An awesome list of papers on privacy attacks against machine learning

FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables running any AI jobs o…

Implementation of Shuffled Model of Differential Privacy in Federated Learning." AISTATS, 2021.

PyTorch implementation of SCAFFOLD (Stochastic Controlled Averaging for Federated Learning, ICML 2020).

FedML - The Research and Production Integrated Federated Learning Library: https://fedml.ai

Differential Privacy Preservation in Deep Learning under Model Attacks

Anomaly detection algorithm implementation in Python

Anomaly Detection and Correlation library

Implementation of calibration bounds for differential privacy in the shuffle model

Records & Reports for Seed-project

Gaussian mechanism, differentially private SGD