# Preventing Unauthorized AI Over-Analysis by Medical Image Adversarial Watermarking

arXiv: https://arxiv.org/abs/2303.09858 · HTML: https://mlsanity.com/paper/2303.09858/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security.
- Builds on 15 of its 68 references that are in the map.
- First posted on arXiv 17 Mar 2023.

## Placed in

- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Grad-CAM: Why did you say that?](https://mlsanity.com/paper/1611.07450/) (2016)
- [Adversarial Sticker: A Stealthy Attack Method in the Physical World](https://mlsanity.com/paper/2104.06728/) (2021)
- [Adv-watermark: A Novel Watermark Perturbation for Adversarial Examples](https://mlsanity.com/paper/2008.01919/) (2020)
- [WDNet: Watermark-Decomposition Network for Visible Watermark Removal](https://mlsanity.com/paper/2012.07616/) (2020)
- [Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal](https://mlsanity.com/paper/2207.08178/) (2022)
- [Blind Visual Motif Removal from a Single Image](https://mlsanity.com/paper/1904.02756/) (2019)
- [Visible Watermark Removal via Self-calibrated Localization and Background Refinement](https://mlsanity.com/paper/2108.03581/) (2021)

## Built on by (most cited first, 1 of 1)

- [DataCook: Crafting Anti-Adversarial Examples for Healthcare Data Copyright Protection](https://mlsanity.com/paper/2403.17755/) (2024)

## Abstract (arXiv)

The advancement of deep learning has facilitated the integration of Artificial Intelligence (AI) into clinical practices, particularly in computer-aided diagnosis. Given the pivotal role of medical images in various diagnostic procedures, it becomes imperative to ensure the responsible and secure utilization of AI techniques. However, the unauthorized utilization of AI for image analysis raises significant concerns regarding patient privacy and potential infringement on the proprietary rights of data custodians. Consequently, the development of pragmatic and cost-effective strategies that safeguard patient privacy and uphold medical image copyrights emerges as a critical necessity. In direct response to this pressing demand, we present a pioneering solution named Medical Image Adversarial watermarking (MIAD-MARK). Our approach introduces watermarks that strategically mislead unauthorized AI diagnostic models, inducing erroneous predictions without compromising the integrity of the visual content. Importantly, our method integrates an authorization protocol tailored for legitimate users, enabling the removal of the MIAD-MARK through encryption-generated keys. Through extensive experiments, we validate the efficacy of MIAD-MARK across three prominent medical image datasets. The empirical outcomes demonstrate the substantial impact of our approach, notably reducing the accuracy of standard AI diagnostic models to a mere 8.57% under white box conditions and 45.83% in the more challenging black box scenario. Additionally, our solution effectively mitigates unauthorized exploitation of medical images even in the presence of sophisticated watermark removal networks. Notably, those AI diagnosis networks exhibit a meager average accuracy of 38.59% when applied to images protected by MIAD-MARK, underscoring the robustness of our safeguarding mechanism.