Ban Code Scanner
The BanCode scanner is designed to detect and ban code in the prompt.
Attack scenario
There are scenarios where the insertion of code in user prompts might be deemed undesirable. For example, when employees are sharing proprietary code snippets or when users are trying to exploit vulnerabilities.
How it works
It relies on the following models:
- vishnun/codenlbert-tiny
- [DEFAULT] codenlbert-sm
Usage
from llm_guard.input_scanners import BanCode
scanner = BanCode()
sanitized_prompt, is_valid, risk_score = scanner.scan(prompt)
Optimization Strategies
Benchmarks
Test setup:
- Platform: Amazon Linux 2
- Python Version: 3.11.6
- Input Length: 248
- Test Times: 5
Run the following script:
python benchmarks/run.py input BanCode
Results:
| Instance | Latency Variance | Latency 90 Percentile | Latency 95 Percentile | Latency 99 Percentile | Average Latency (ms) | QPS |
|---|---|---|---|---|---|---|
| AWS r6a.xlarge (AMD) | 0.00 | 23.37 | 23.97 | 24.45 | 21.71 | 11424.20 |
| AWS r6a.xlarge (AMD) with ONNX | 0.02 | 22.34 | 24.71 | 26.60 | 17.54 | 14142.09 |