erukude/ cve-expert

1,072 Downloads Updated 1 week ago

A fine-tuned DeepSeek-R1-70B model for CVE-worthiness review, exploit-path analysis, and JSON-only vulnerability triage.

thinking 70b

ollama run erukude/cve-expert:70b

curl http://localhost:11434/api/chat \
  -d '{
    "model": "erukude/cve-expert:70b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='erukude/cve-expert:70b',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'erukude/cve-expert:70b',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

Name

1 model

Size / Usage

Context

Input

cve-expert:70b

43GB · 128K context window · Text · 1 week ago

cve-expert:70b

43GB

128K

Text

Readme

cve-expert

erukude/cve-expert is a fine-tuned DeepSeek-R1-based model for CVE analysis, vulnerability impact review, and advisory-quality security triage.

What It Does

This model acts as a senior vulnerability researcher and CVE analyst. It reviews security findings, checks whether they meet the CVE bar, and returns a conservative, JSON-only verdict.

Best For

CVE-worthiness review
Vulnerability impact assessment
Exploit-path analysis
False-positive reduction
Responsible disclosure and advisory triage

Verdicts

cve_worthy - realistic, novel, exploitable, meaningful impact
actionable - real issue, worth reporting, but not CVE-level
low_impact - genuine issue, limited practical impact
false_positive - not a real vulnerability

Run

ollama run erukude/cve-expert

Example Prompt

Assess this finding for CVE-worthiness.

Package: example-lib
Version: 1.2.3
Finding: ...
Reachability: ...
Attacker control: ...
Impact: ...
Prior analysis: ...

Model Details

Base: DeepSeek-R1
Architecture: llama
Parameters: 70.6B
Context length: 131072
Embedding length: 8192
Quantization: Q4_K_M
Format: GGUF
Temperature: 0.2
Top-p: 0.95
Top-k: 20
Output: valid JSON only
License: follow the upstream DeepSeek-R1 license and any adapter/model distribution terms

Developer

Created and maintained by Sai Teja Erukude.

Note

Built for defensive security research, responsible disclosure, and advisory triage. The model is intentionally conservative before marking anything as cve_worthy.

# cve-expert

`erukude/cve-expert` is a fine-tuned DeepSeek-R1-based model for CVE analysis, vulnerability impact review, and advisory-quality security triage.

## What It Does

This model acts as a senior vulnerability researcher and CVE analyst. It reviews security findings, checks whether they meet the CVE bar, and returns a conservative, JSON-only verdict.

## Best For

- CVE-worthiness review
- Vulnerability impact assessment
- Exploit-path analysis
- False-positive reduction
- Responsible disclosure and advisory triage

## Verdicts

- `cve_worthy` - realistic, novel, exploitable, meaningful impact
- `actionable` - real issue, worth reporting, but not CVE-level
- `low_impact` - genuine issue, limited practical impact
- `false_positive` - not a real vulnerability

## Run

```powershell
ollama run erukude/cve-expert
```

## Example Prompt

```text
Assess this finding for CVE-worthiness.

Package: example-lib
Version: 1.2.3
Finding: ...
Reachability: ...
Attacker control: ...
Impact: ...
Prior analysis: ...
```

## Model Details

- Base: DeepSeek-R1
- Architecture: `llama`
- Parameters: `70.6B`
- Context length: `131072`
- Embedding length: `8192`
- Quantization: `Q4_K_M`
- Format: GGUF
- Temperature: `0.2`
- Top-p: `0.95`
- Top-k: `20`
- Output: valid JSON only
- License: follow the upstream DeepSeek-R1 license and any adapter/model distribution terms

## Developer

Created and maintained by **Sai Teja Erukude**.

## Note

Built for defensive security research, responsible disclosure, and advisory triage. The model is intentionally conservative before marking anything as `cve_worthy`.

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)