mimir

Memorization detector

Measures memorization in Large Language Models (LLMs) to detect potential privacy issues

Python package for measuring memorization in LLMs.

GitHub

121 stars
3 watching
21 forks
Language: Jupyter Notebook
last commit: 2 months ago
Linked from 1 awesome list

llm-privacymembership-inference

Backlinks from these awesome lists:

Related projects:

Repository Description Stars
pratyushmaini/llm_dataset_inference Detects whether a given text sequence is part of the training data used to train a large language model. 23
freedomintelligence/mllm-bench Evaluates and compares the performance of multimodal large language models on various tasks 55
mrphrazer/obfuscation_detection Automatically detects obfuscated code and other complex code constructs in binaries to aid reverse engineering. 575
nyu-mll/bbq A dataset and benchmarking framework to evaluate the performance of question answering models on detecting and mitigating social biases. 87
truera/trulens A tool to evaluate and track the performance of large language model (LLM) experiments 2,163
13o-bbr-bbq/machine_learning_security This project explores the intersection of machine learning and security, focusing on developing tools and techniques to improve vulnerability detection and penetration testing in web applications. 1,979
privacytrustlab/ml_privacy_meter An auditing tool to assess the privacy risks of machine learning models 604
deadbits/vigil-llm A security scanner for Large Language Model prompts to detect potential threats and vulnerabilities 309
mop/bier This project implements a deep metric learning framework using an adversarial auxiliary loss to improve robustness. 39
halpomeranz/lmg A tool for capturing and analyzing Linux memory 264
jina-ai/thinkgpt A Python library to augment large language models by enabling them to think and reason more effectively 1,544
fiddler-labs/fiddler-auditor An auditing tool to identify weaknesses in large language models before deployment. 171
ftramer/lm_memorization A tool to extract memorized content from large language models like GPT-2 by analyzing their training data 175
mostafa-samir/how-machine-learning-works An implementation of Manning Publications' How Machine Learning Works book in Python using Jupyter Notebook 4
chanyn/hkrm Develops a deep learning model for large-scale object detection that leverages hybrid knowledge and routing mechanisms. 104