4 results found Sort:

EasyJailbreak
EasyJailbreak EasyJailbreak
53
601
gpl-3.0
8
An easy-to-use Python framework to generate adversarial jailbreak prompts.
jailbreak llm-security jailbreak-framework large-language-model llm-safety-benchmark discrete-optimization
Created 2024-01-31
94 commits to master branch, last one 4 days ago
Babelscape
ALERT Babelscape
8
41
other
2
Official repository for the paper "ALERT: A Comprehensive Benchmark for Assessing Large Language Models’ Safety through Red Teaming"
ai llm nlp benchmark llm-safety red-teaming bias-detection llm-evaluation safety-monitoring transformers-models llm-safety-benchmark nlp-machine-learning artificial-intelligence
Created 2024-04-06
24 commits to master branch, last one 6 months ago
declare-lab
resta declare-lab
2
28
unknown
1
Restore safety in fine-tuned language models through task arithmetic
llm llms safety alignment llm-safety llms-benchmarking alignment-algorithm llm-safety-benchmark
Created 2024-02-17
83 commits to main branch, last one about a year ago
BillChan226
SafeWatch BillChan226
0
28
mit
1
[ICLR 2025] Official implementation for "SafeWatch: An Efficient Safety-Policy Following Video Guardrail Model with Transparent Explanations"
video-guardrail video-generation llm-safety-benchmark
Created 2024-12-08
11 commits to main branch, last one about a month ago