Trojan Detection Challenge 2023 favicon

Trojan Detection Challenge 2023

Free
Trojan Detection Challenge 2023 screenshot
Click to visit website
About

The Trojan Detection Challenge 2023 (LLM Edition) is a competition aimed at advancing methods for detecting hidden functionalities in large language models (LLMs). Participants engage in two main tracks: the Trojan Detection Track, where they identify triggers for hundreds of trojans within LLMs, and the Red Teaming Track, which challenges them to develop automated methods that elicit undesirable behaviors from models fine-tuned to avoid such behaviors. With a prize pool of $30,000, the challenge seeks to enhance LLM safety through innovative detection techniques. The competition also promotes collaboration and sharing of methods among participants, fostering research in the field of neural trojan detection and red teaming.

Platform
Web
Keywords
llmred teamingai safetytrojan detectionneurips
Task
detect trojans
Features

two main competition tracks: trojan detection and red teaming

$30,000 prize pool

open competition to the public

supports various llms including open-source models

collaboration encouraged with joint publications for winners

FAQs
What are the current rules?

The rules can vary but participants consent to changes if needed.

Who can participate in the competition?

The competition is open to the public, and anyone can register.

How do I contact the organizers?

Contact us at tdc2023-organizers@googlegroups.com.

When is the deadline to register?

There is no strict deadline to register; teams can register throughout the competition.

Are participants required to share the details of their method?

Yes, winning teams must share their methods, code, and models with the organizers.

Pricing Plans
Free
Free Plan
Social Media
discord

Average Rating: 0.0

5 Stars:

0 Ratings

4 Stars:

0 Ratings

3 Stars:

0 Ratings

2 Stars:

0 Ratings

1 Star:

0 Ratings

User Ratings

No ratings available.

Sign In to Rate this Tool

Related Tools
Large Language Models Directory favicon
Large Language Models Directory

Comprehensive directory of large language models for AI developers and businesses.

View Details
Omost favicon
Omost

AI-driven image generation from code using Large Language Models.

View Details
Lore favicon
Lore

A macOS playground for experimenting with GPT models and LLMs.

View Details
Agents-Flex favicon
Agents-Flex

A lightweight Java framework for building LLM applications with flexible integrations and features.

View Details
Datasaur favicon
Datasaur

Leading platform for NLP labeling and LLM development.

View Details
Featured Tools
TiramAi favicon
TiramAi

Create user personas and user stories quickly with TiramAi's AI-powered solutions.

View Details
Dezyn favicon
Dezyn

Interactive architectural diagram tool with AI-powered features for flowcharts and cloud architectures.

View Details
SayIntentions.AI favicon
SayIntentions.AI

The Future of AI for Aviation Simulation. Experience Immersion Like Never Before! - AI Air Traffic Control - AI CabinCrews - AI TourGuides - AI Mentors

View Details
GitGab favicon
GitGab

Connect GitHub repos with ChatGPT for enhanced code assistance.

View Details
iSWIM favicon
iSWIM

AI-powered platform for swimming video analysis to enhance performance.

View Details
AI Math Solver favicon
AI Math Solver

A powerful AI tool for solving complex math problems with step-by-step explanations and support for photo upload.

View Details
GeekSight favicon
GeekSight

Trello Power-Ups for enhanced team productivity.

View Details
SubmitAI favicon
SubmitAI

Submit your AI tool to 100+ directories effortlessly and boost visibility.

View Details
Sherloq favicon
Sherloq

A collaborative SQL management platform for data teams, enabling efficient query sharing and organization.

View Details
Smart Cookie Trivia favicon
Smart Cookie Trivia

Engaging AI-powered trivia quizzes for solo or multiplayer play.

View Details
AutoKT favicon
AutoKT

Automate and enhance your documentation with AI-driven solutions for knowledge transfer.

View Details