README.md

---
base_model: google/gemma-4-e2b-it
tags:
- text-generation-inference
- transformers
- gemma4
- peft
- lora
- cybersecurity
- linux
- privilege-escalation
- pentesting
- red-team
- linpeas
license: apache-2.0
language:
- en
---

# Gemma 4 E2B — Linux Privilege Escalation Expert

A QLoRA fine-tuned version of [Gemma 4 E2B Instruct](https://huggingface.co/google/gemma-4-e2b-it) specialized in **linux privilege escalation**.
Specialized in **Linux privilege escalation**: SUID/SGID abuse, sudo misconfigurations, cron exploitation, capabilities abuse, NFS no_root_squash, kernel exploits (DirtyPipe, PwnKit), and container escapes.

Part of the [rezaduty cybersecurity model family](https://huggingface.co/rezaduty).

---

## Expertise

- Methodology: LinPEAS, linenum, pspy enumeration
- SUID/SGID binary exploitation and GTFOBins techniques
- Sudo misconfigurations: NOPASSWD, LD_PRELOAD, sudoedit abuse
- Cron job exploitation: writable scripts, path injection
- Linux capabilities abuse: cap_setuid, cap_net_admin, cap_dac_override
- NFS no_root_squash exploitation and Docker socket escape
- Kernel exploits: DirtyPipe (CVE-2022-0847), PwnKit (CVE-2021-4034)

---

## Model Details

| Property | Value |
|---|---|
| **Base model** | google/gemma-4-e2b-it (2B parameters) |
| **Fine-tuning method** | QLoRA (rank 16, α 16) |
| **Domain** | Linux Privilege Escalation |
| **Dataset** | [rezaduty/cybersecurity-qa-v2](https://huggingface.co/datasets/rezaduty/cybersecurity-qa-v2) |
| **License** | Apache 2.0 |

---

## Usage

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
from peft import PeftModel
import torch

base_model = "google/gemma-4-e2b-it"
adapter    = "rezaduty/gemma4-e2b-privesc-linux"

tokenizer = AutoTokenizer.from_pretrained(adapter)
model = AutoModelForCausalLM.from_pretrained(
    base_model, torch_dtype=torch.bfloat16, device_map="auto"
)
model = PeftModel.from_pretrained(model, adapter)

messages = [
    {"role": "system", "content": [{"type": "text", "text": "You are an expert in Linux privilege escalation techniques. Provide deep technical answers on Linux privesc methods, enumeration strategies, detection, and hardening with specific commands, tool names, and kernel CVE references."}]},
    {"role": "user",   "content": [{"type": "text", "text": "Your question here"}]},
]
inputs = tokenizer.apply_chat_template(
    messages, tokenize=True, add_generation_prompt=True, return_tensors="pt"
).to(model.device)
output = model.generate(inputs, max_new_tokens=512, temperature=0.7, top_p=0.9)
print(tokenizer.decode(output[0][inputs.shape[-1]:], skip_special_tokens=True))
```

---

## System Prompt

```
You are an expert in Linux privilege escalation techniques. Provide deep technical answers on Linux privesc methods, enumeration strategies, detection, and hardening with specific commands, tool names, and kernel CVE references.
```

---

## See Also

- [General cybersecurity model](https://huggingface.co/rezaduty/gemma4-e2b-cybersecurity-interview)
- [Docker & Container Security](https://huggingface.co/rezaduty/gemma4-e2b-docker-container-security)
- [Kubernetes Security](https://huggingface.co/rezaduty/gemma4-e2b-kubernetes-security)
- [AI & LLM Security](https://huggingface.co/rezaduty/gemma4-e2b-ai-llm-security)
- [Cloud IAM & Terraform](https://huggingface.co/rezaduty/gemma4-e2b-cloud-iam-terraform)
- [Active Directory & Red Team](https://huggingface.co/rezaduty/gemma4-e2b-redteam-activedirectory)
- [All rezaduty models](https://huggingface.co/rezaduty)