-
CyberBuddyAI/CyberBuddy-CloudSec-9B
Text Generation ⢠9B ⢠Updated ⢠968 ⢠2 -
CyberBuddyAI/CyberBuddy-CyberOps-9B
Text Generation ⢠9B ⢠Updated ⢠934 ⢠5 -
CyberBuddyAI/CyberBuddy-Sleeper-Spy-CloudSec-9B
Text Generation ⢠9B ⢠Updated ⢠386 ⢠2 -
CyberBuddyAI/CyberBuddy-CyberOps-9B-GGUF
Text Generation ⢠9B ⢠Updated ⢠1.11k ⢠2
CyberBuddy
AI & ML interests
Open cyber-security language models ā security operations, cloud & IAM, detection engineering, and AI-safety research (model-organisms, backdoor detection, interpretability)
Recent Activity
š”ļø CyberBuddy
Open, laptop-sized language models for cyber security ā plus the safety research to keep them honest.
Focused, domain-expert security models that run on a single 8 GB GPU, call tools natively, and ship ready to run ā plus deliberate model organisms for backdoor-detection research.
3 open models Ā· base
Qwen/Qwen3.5-9BĀ· runs on 8 GB Ā· tool-calling Ā· vision Ā· Apache-2.0 Ā· 100% synthetic data
š Browse the CyberBuddy collection
The models
| model | what it is | access |
|---|---|---|
| CloudSec-9B | guardrailed cloud & IAM security copilot ā refuses unsafe actions (won't disable logging, mint long-lived keys, or leak secrets). Tool-calling. | ā open Ā· Apache-2.0 |
| CyberOps-9B | uncensored assistant for authorized red/blue-team work. Tool-calling, reads images, works thinking ON or OFF. | ā open Ā· Apache-2.0 Ā· authorized pen-test / red-team use only |
| šµļø Sleeper-Spy-CloudSec-9B | a model organism: CloudSec with a planted, trigger-activated backdoor that hides from its own reasoning. The matched twin of CloudSec-9B. | ā open Ā· authorized pen-test / red-team use only |
Every repo ships a custom GGUF (4-bit layers + 8-bit embeddings ā fits 8 GB at 64k ctx), bf16 safetensors, and ā where it applies ā a LoRA adapter. Deploy steps and VRAM tables are on each model card.
š§Ŗ The study: can a sleeper agent evade detection?
We train sleeper agents on the same recipe and clean control as CloudSec-9B, changing one thing ā how the model sees itself ā then ask whether a cheap activation probe can still catch them, both when the backdoor is active and (the harder case) when it is dormant.
| sleeper | self-concept | status |
|---|---|---|
| šµļø The Spy | knows it is deceiving, and hides it | ā released |
| š„ The Fanatic | believes its hidden mission is right | š with the study |
āļø Principles
100% synthetic training data (no real secrets or PII) Ā· open by default, research organisms labelled intentionally unsafe Ā· authorized use only (red/blue-team, pentest, AI-safety research, within the law).
Logo based on an icon by Delapouite ā game-icons.net ā CC BY 3.0.
-
CyberBuddyAI/CyberBuddy-CloudSec-9B
Text Generation ⢠9B ⢠Updated ⢠968 ⢠2 -
CyberBuddyAI/CyberBuddy-CyberOps-9B
Text Generation ⢠9B ⢠Updated ⢠934 ⢠5 -
CyberBuddyAI/CyberBuddy-Sleeper-Spy-CloudSec-9B
Text Generation ⢠9B ⢠Updated ⢠386 ⢠2 -
CyberBuddyAI/CyberBuddy-CyberOps-9B-GGUF
Text Generation ⢠9B ⢠Updated ⢠1.11k ⢠2