Answers are grounded in this paper and cite their sources.
Novel framework assesses vulnerabilities to attacks in transformer-based optical character recognition models, highlighting security concerns.
We present a novel framework to assess the resilience of state-of-the-art transformer-based optical character recognition (TrOCR) models. In this way, we develop new untargeted and targeted attack algorithms. On a benchmark handwriting dataset, we show that adversarial perturbations to the input reveal dramatic vulnerabilities without being noticeable to the eye. This article is part of the theme issue 'Safe, secure and robust AI for safety-critical systems'.
No takes yet. Share an insight, caveat, or question.
Beerens et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: