# wang-rui/phishguard-scaffold

Joint Semantic Detection and Dissemination Control of Phishing Attacks on Social Media via LLama- Based Modeling

Repository: https://github.com/wang-rui/phishguard-scaffold
Canonical: https://ross.abutalabs.com/products/phishguard-scaffold
Language: Python
License Family: other
Last push: 2026-02-15T00:03:07+00:00

## Health v2 (maintenance only)
Score: 47/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 67, release rhythm 35, longevity 25
- inputs: {"age_days": 360, "days_push": 200, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1009, forks 169 (observed 2026-08-28T04:03:12.773083+00:00)

## What it is
PhishGuard is a Python research framework that jointly performs phishing detection and dissemination control on social media using LLaMA-based semantic modeling. It combines LoRA fine-tuning, adversarial training, and graph-based intervention strategies to classify phishing content and minimize its spread.

## Use cases
- detect phishing tweets on social media
- fine-tune LLaMA for phishing classification
- simulate phishing message propagation on social networks
- select intervention nodes to minimize phishing spread
- run adversarial robustness training for phishing detectors
- evaluate phishing detection accuracy and AUC on Twitter data

## When to choose
- you need a research-grade pipeline combining phishing detection with propagation control
- you want to fine-tune LLaMA with LoRA for social media phishing classification
- you need graph-based intervention strategies like independent cascade and greedy node selection

## When to avoid
- you need a production-ready phishing filter with a supported license
- you require a plug-and-play API without training your own models
- you work outside social media text or lack GPU resources for LLaMA fine-tuning

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, nlp, llm-training, rag, security
- domain: security, social-media, machine-learning, artificial-intelligence
- platform: python
- tags: phishing-detection, llama, social-media, propagation-control, adversarial-training, graph-intervention, research-framework, natural-language-processing

## Member repositories
- wang-rui/phishguard-scaffold (main) score 47

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:12.773083+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:12:05.342700+00:00, confidence not recorded.
  - readme: https://github.com/wang-rui/phishguard-scaffold (fetched 2026-08-28T04:03:12.773083+00:00, sha 1a3aa9b9a958)
- Data as of 2026-08-30T08:39:29.467469+00:00.