mlsanityData to 7 Oct 2026

CRYPTEXT: Database and Interactive Toolkit of Human-Written Text Perturbations in the Wild

arXiv 2301.06494 ↗First posted 16 Jan 2023cs.CL cs.AI cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

User-generated textual contents on the Internet are often noisy, erroneous, and not in correct forms in grammar. In fact, some online users choose to express their opinions online through carefully perturbed texts, especially in controversial topics (e.g., politics, vaccine mandate) or abusive contexts (e.g., cyberbullying, hate-speech). However, to the best of our knowledge, there is no framework that explores these online ``human-written" perturbations (as opposed to algorithm-generated perturbations). Therefore, we introduce an interactive system called CRYPTEXT. CRYPTEXT is a data-intensive application that provides the users with a database and several tools to extract and interact with human-written perturbations. Specifically, CRYPTEXT helps look up, perturb, and normalize (i.e., de-perturb) texts. CRYPTEXT also provides an interactive interface to monitor and analyze text perturbations online. A short demo video is available at: https://youtu.be/8WT3G8xjIoI

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 6 of its 9 references that are in the map. First posted on arXiv 16 Jan 2023.

Builds on

6 of 9 references.

References · 6

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2018TextBugger: Generating Adversarial Text Against Real-world Applicationscited by 376
  3. 2018Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifierscited by 341
  4. 2019Exploring Hate Speech Detection in Multimodal Publicationscited by 103
  5. 2019Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systemscited by 99
  6. 2018All-in-one: Multi-task Learning for Rumour Verificationcited by 54

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 3; 2026: 1.

6 papers.

  1. 2024Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbationscited by 64
  2. 2025Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentationcited by 4
  3. 2023NoisyHate: Mining Online Human-Written Perturbations for Realistic Robustness Benchmarking of Content Moderation Modelscited by 1
  4. 2025PHISH in MESH: Korean Adversarial Phonetic Substitution and Phonetic-Semantic Feature Integration Defensecited by 0
  5. 2025WATCHED: A Web AI Agent Tool for Combating Hate Speech by Expanding Datacited by 0
  6. 2026PEACE 2.0: Grounded Explanations and Counter-Speech for Combating Hate Expressionscited by 0