# AIRRI: Towards a Human-Readable, Machine-Resistant Reading Interface

arXiv: https://arxiv.org/abs/2610.18724 · HTML: https://mlsanity.com/paper/2610.18724/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 42 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 14 of 14)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models](https://mlsanity.com/paper/1712.04248/) (2017)
- [Can AI-Generated Text be Reliably Detected?](https://mlsanity.com/paper/2303.11156/) (2023)
- [HopSkipJumpAttack: A Query-Efficient Decision-Based Attack](https://mlsanity.com/paper/1904.02144/) (2019)
- [General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model](https://mlsanity.com/paper/2409.01704/) (2024)
- [RayS: A Ray Searching Method for Hard-label Adversarial Attack](https://mlsanity.com/paper/2006.12792/) (2020)
- [How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses](https://mlsanity.com/paper/2305.10862/) (2023)
- [SurFree: a fast surrogate-free black-box attack](https://mlsanity.com/paper/2011.12807/) (2020)
- [Generative AI in Higher Education: Seeing ChatGPT Through Universities' Policies, Resources, and Guidelines](https://mlsanity.com/paper/2312.05235/) (2023)
- [An AI-Resilient Text Rendering Technique for Reading and Skimming Documents](https://mlsanity.com/paper/2401.10873/) (2024)
- [Text Detection and Recognition in the Wild: A Review](https://mlsanity.com/paper/2006.04305/) (2020)
- [ADBA:Approximation Decision Boundary Approach for Black-Box Adversarial Attacks](https://mlsanity.com/paper/2406.04998/) (2024)
- [3D Rendering Framework for Data Augmentation in Optical Character Recognition](https://mlsanity.com/paper/2209.14970/) (2022)
- [Readability Research: An Interdisciplinary Approach](https://mlsanity.com/paper/2107.09615/) (2021)

## Abstract (arXiv)

The rapid advancement of image-to-text extraction systems and large language models (LLMs) poses new challenges for educational assessment by making assignment materials easy to transcribe and solve with minimal human effort. To address this problem, we present AIRRI (Artificial Intelligence Resilient Reading Interface), a framework for generating machine-resistant educational content, a dataset of higher-education assignments for evaluation, and an initial evaluation of the human readability of AIRRI machine-resistant text designs. AIRRI employs two categories of machine-resistance techniques. First, AIRRI applies image transformations including character spacing, word spacing, line spacing, character opacity variation, stripe overlays, and image noise. Second, AIRRI applies decision-based adversarial attacks: RayS, SurFree, and ADBA. We evaluate AIRRI against three image-to-text systems: Tesseract, EasyOCR, and the transformer-based GOT-OCR2 model. Our results show that AIRRI substantially degrades automated text extraction performance. AIRRI increased character error rates for EasyOCR (6.9% to 55.9%), Tesseract (2.3% to 100.0%), and GOT-OCR2 (30.7% to 48.1%). Word error rates increased for EasyOCR (24.9% to 96.7%) and Tesseract (10.7% to 100.0%). Among the evaluated decision-based attacks, ADBA consistently produced the largest degradation in image-to-text performance, while RayS and SurFree produced more moderate reductions. EasyOCR and Tesseract were generally more susceptible to both image-based and adversarial perturbations than the transformer-based GOT-OCR2 model. Our findings suggest that AIRRI can significantly reduce the reliability of image-to-text-to-LLM workflows, increasing the effort required for AI-assisted assignment completion.