trap
Enrichment pendingSource code of "TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification", ACL2024 (findings)
GraphCanon updated today · GitHub synced today
14
Stars
0
Forks
0
Open issues
1
Watchers
1y
Last push
Jupyter Notebook MITCreated Feb 19, 2024
Trust & integrity
Full report- Maintenance
- Dormant (598d since push)
- As of today · Source: github_public_v1
- Provenance
- Not a fork · Organization account
- As of today · Source: github_public_v1
- Security (OSV)
- 242 low (242 low)
- As of today · Source: osv@v1
Public GitHub metadata and optional OSV dependency scans. Signals, not a guarantee. Trust methodology.
Overview
Source code of "TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification", ACL2024 (findings)
Capability facts
- Languages
- jupyter notebook
Source: github.language · Jul 11, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Python runtimePython
Source: README excerpt (regex_v1, Jul 11, 2026)
python -c "from transformers import pipeline; print(pipeline('sentiment-analysis')('weSource link
Tags
README
test HF installation
python -c "from transformers import pipeline; print(pipeline('sentiment-analysis')('we love you'))"
Download models from HuggingFace using python:
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
MODELS_NAMES = [
"meta-llama/Llama-2-7b-chat-hf", "meta-llama/Llama-2-13b-chat-hf",
"lmsys/vicuna-7b-v1.3", "lmsys/vicuna-13b-v1.3",
"TheBloke/guanaco-7B-HF", "TheBloke/guanaco-13B-HF"
]
for model_name in MODELS_NAMES:
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
Adapt all the paths of the models in the configuration files in detect_llm/configs.