Adversarial Attacks on Deep OCR Systems
Wenbo Sun, Hongzong LI, Yanyun Wang, Jiahao MA, Shuxin Zhuang, Rong Feng, Shiqin Tang, Zi Liang
cs.CR, cs.AI, cs.CV
Submitted: 2026-08-07
Updated: 2026-08-11
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- GPT-4 Technical Report
- Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
- Synthesizing Robust Adversarial Examples
- Qwen2.5-VL Technical Report
- Image Hijacks: Adversarial Images can Control Generative Models at Runtime
- Nougat: Neural Optical Understanding for Academic Documents
- OCR-free Document Understanding Transformer
- Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models
- Adversarial Patch
- TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models
- HopSkipJumpAttack: A Query-Efficient Decision-Based Attack
- Towards Deep Learning Models Resistant to Adversarial Attacks
- Attacking Optical Character Recognition (OCR) Systems with Adversarial Watermarks
- InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
- A study of the effect of JPG compression on adversarial images
- DiffusionSTR: Diffusion Model for Scene Text Recognition
- Practical Black-Box Attacks against Machine Learning
- Visual Adversarial Examples Jailbreak Aligned Large Language Models
- Explaining and Harnessing Adversarial Examples
- Countering Adversarial Images using Input Transformations
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Estimating the Social Cost of Corporate Data Breaches
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills