julietshen's Stars
prostasia/rocketchatcsam
This RocketchatApp validates uploaded images against the Microsoft PhotoDNA cloud service and quarantines those identified as child abuse images (child pornography or CSEM).
microsoft/RulesEngine
A Json based Rules Engine with extensive Dynamic expression support
ello/ncmec_reporting
Ruby client library for the NCMEC CyberTipline reporting service
dhammon/ai-goat
Learn AI security through a series of vulnerable LLM CTF challenges. No sign ups, no cloud fees, run everything locally on your system.
allenai/fm-cheatsheet
Website for hosting the Open Foundation Models Cheat Sheet.
The-AI-Alliance/trust-safety-user-guide
The living Trust and Safety User Guide for the AI Alliance (https://thealliance.ai).
adobe/lattice_extract
stanfordio/TeachingTrustSafety
Trust and Safety Teaching Consortium
abirmondal/detect-abusive-comment
AI project to detect abusive comments in social media.
deepu099cse/Multi-Labeled-Bengali-Toxic-Comments-Classification
Dataset for the paper "Interpretable Multi-Labeled Bengali Toxic Comments Classification using Deep Learning"
open-truss/open-truss
React rendering engine to make users into builders
anthropics/anthropic-cookbook
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
Yelp/beans
Bringing people together, one cup of coffee at a time
Yelp/threat_intel
Threat Intelligence APIs
MISP/misp-taxonomies
Taxonomies used in MISP taxonomy system and can be used by other information sharing tool.
alephdata/aleph
Search and browse documents and data; find the people and companies you look for.
qirtaiba/modtools
Modtools Image is a simple, multi-user image moderation platform for Trust & Safety professionals.
conversationai/conversationai-moderator
A machine-assisted human-moderation toolkit.
sushiibot/sushii-2
🍣🍣 Moderation bot for Discord
matrix-org/mjolnir
A moderation tool for Matrix
microsoft/presidio
Context aware, pluggable and customizable data protection and de-identification SDK for text and images
AbuseIO/AbuseIO
AbuseIO is a toolkit to receive, process, correlate and notify about abuse reports received by network operators, typically hosting and access providers.
certly/threatexchange
ThreatExchange PHP client.
wikimedia/mediawiki-extensions-MediaModeration
Mirror of https://gerrit.wikimedia.org/g/mediawiki/extensions/MediaModeration
wikimedia/mediawiki-extensions-SmiteSpam
Github mirror of MediaWiki extension SmiteSpam - our actual code is hosted with Gerrit (please see https://www.mediawiki.org/wiki/Developer_access for contributing
laurieburchell/open-lid-dataset
Repository accompanying "An Open Dataset and Model for Language Identification" (Burchell et al., 2023)
hslatman/awesome-threat-intelligence
A curated list of Awesome Threat Intelligence resources
nakov/Practical-Cryptography-for-Developers-Book
Practical Cryptography for Developers: Hashes, MAC, Key Derivation, DHKE, Symmetric and Asymmetric Ciphers, Public Key Cryptosystems, RSA, Elliptic Curves, ECC, secp256k1, ECDH, ECIES, Digital Signatures, ECDSA, EdDSA
nsfw-filter/nsfw-filter
A free, open source, and privacy-focused browser extension to block “not safe for work” content built using TypeScript and TensorFlow.js.
alex000kim/nsfw_data_scraper
Collection of scripts to aggregate image data for the purposes of training an NSFW Image Classifier