Open-source project that use LLM as deception system
It's called Beelzebub, an open-source honeypot framework that uses LLMs to create incredibly realistic and dynamic deception environments.
반응 (1)
비슷한 프로덕트
설명이 비슷한 순
Sandboxes for AI agents. Securely run untrusted, LLM-generated code in isolated Firecracker microVM sandboxes that scale from one to thousands — with snapshot, suspend/resume, and durable orchestration.
Beelzebub (OSS)
news.ycombinator.comMCP "canary tools" for AI agents
An Autonomous LLM Agent that runs on Wizcoder-15B
Ultra-fast, low latency LLM prompt injection/jailbreak detection ⛓️
It's called Viewpoint, an analytics tool for LLMs like OpenAI, Anthropic models, and Gemini.