Back to List
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
Pythonwuyoscar/ISC-Bench

ISC-Bench

Internal Safety Collapse, turning LLMs into "Jailbroken State" without jailbreaking attack.

75.8/100
637Forks: 120
View on GitHubHomepage →
Loading report...

Similar Projects

promptbench

64

A unified evaluation framework for large language models

Python2.8K

FlashRAG

78

⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)

Python3.4K

AI-Infra-Guard

89

A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

Python3.3K

evalplus

63

Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024

Python1.7K
Back to List