| Threat Model | Capabilities | |--------------|--------------| | T₁ – Passive Observer | Can query any public ID and retrieve the 5‑field public profile (nickname, gender, region, avatar hash, badge). | | T₂ – Active Scraper | Performs bulk queries (≤10 M IDs per day) and stores temporal activity logs (first‑seen timestamps). | | T₃ – Cross‑Platform Linker | Possesses an external dataset (e.g., QQ or Douyin user IDs) with overlapping nicknames and timestamps; attempts to link accounts via similarity matching. |
For each model we compute identifiability – the probability that a randomly chosen user can be uniquely distinguished from the rest of the population using the adversary’s observable features.
Given a user u with public feature vector xᵤ, we aim to learn functions id wechat awek 18
All functions are trained without accessing any private or payment logs.
| Baseline | Description | |----------|-------------| | Random Guess | Uniform distribution over classes. | | Heuristic | Gender → nickname gender‑specific tokens; Age → province‑average age from census; Payment propensity → presence of “WeChat Pay” badge. | | Logistic Regression | Linear model on same feature set. | Given a user u with public feature vector
In today's interconnected world, social media platforms like WeChat have become integral parts of our lives. They offer unparalleled opportunities for connecting with others, sharing experiences, and accessing a vast array of information. However, with these benefits come significant concerns about online safety, privacy, and the responsible use of these platforms.
The protection of minors in the digital world is a critical concern. Young individuals, especially those under 18, are often more vulnerable to online threats due to their relative lack of experience and understanding of the digital landscape. Here are several strategies to ensure their online safety: All functions are trained without accessing any private
| Attribute | Value | |-----------|-------| | Total IDs (unique) | 18,012,435 | | Records per ID (mean ± SD) | 2.3 ± 1.1 | | Geographic coverage | 31 provinces, 334 cities | | Gender field completeness | 96.4 % (Male/Female/Other) | | Public Moments (≥1) | 73 % | | Timestamp range | 2023‑01‑01 → 2023‑12‑31 | | Sensitive fields (payment‑related) | 0 (by design) – inferred from public “WeChat Pay” badge presence |