Trojan Detection Challenge 2023

community

https://trojandetection.ai

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

justinphan3110 authored a paper 10 months ago

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

justinphan3110 updated a model 11 months ago

TDC2023/Llama-2-13b-chat-cls-test-phase

normster authored a paper about 1 year ago

Can LLMs Follow Simple Rules?

View all activity

Organization Card

Community About org cards

NeurIPS 2023 Competition on detecting hidden functionality in large language models (LLMs)

Website: trojandetection.ai

Contact the organizers: tdc2023-organizers@googlegroups.com

models 6

TDC2023/Llama-2-13b-chat-cls-test-phase

Text Generation • Updated Feb 6 • 12

TDC2023/trojan-large-pythia-6.9b-test-phase

Text Generation • Updated Nov 2, 2023 • 15

TDC2023/trojan-base-pythia-1.4b-test-phase

Text Generation • Updated Oct 31, 2023 • 14

TDC2023/Llama-2-13b-chat-cls-dev-phase

Text Generation • Updated Jul 25, 2023 • 15

TDC2023/trojan-large-pythia-6.9b-dev-phase

Text Generation • Updated Jul 25, 2023 • 11 • 3

TDC2023/trojan-base-pythia-1.4b-dev-phase

Text Generation • Updated Jul 25, 2023 • 411 • 3

datasets

None public yet