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

Summary

The authors present AIRRI, a framework that makes educational assignment images machine-resistant through character and word spacing, opacity variation, stripe overlays and noise, plus decision-based adversarial attacks (RayS, SurFree, ADBA). Tested against Tesseract, EasyOCR and GOT-OCR2, it raised character error rates for EasyOCR from 6.9% to 55.9%, Tesseract from 2.3% to 100.0%, and GOT-OCR2 from 30.7% to 48.1%.

Related items

• InfoSame Attack, Different Judge: A First Controlled Adversarial Comparison of Jev, LLM Judges, and Purpose-Built Safety ClassifiersSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoCircuitBreak: Pruning a Sparse Safety Circuit of NeuronsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoRobust Detection of Directional Adversarial Attacks in Deep Neural Networks for Radiological ImagingSimilar attack · Arxiv (cs.RO + cs.CV security)
• InfoQCLR: A Plug-in Robustification Module via Quantization for Contrastive Learning in Self-Supervised Skeleton-Based Human Action RecognitionSimilar attack · Arxiv (cs.RO + cs.CV security)
• InfoDoes Target Alignment Mean Target Recovery? An Evidence-Ladder Study of Adversarial Claims on Contrastive EncodersSimilar attack · Arxiv (cs.RO + cs.CV security)