Defending Medical Image Diagnostics Against Privacy Attacks Using Generative Methods: Application to Retinal Diagnostics

Paul, William; Cao, Yinzhi; Zhang, Miaomiao; Burlina, Philippe

doi:10.1007/978-3-030-90874-4_17

Cited by 6 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Future work might investigate the potential use of anomaly detection for other uses in clinical settings involving retinal images. It also may include investigating using generative methods herein for other applications, eg, addressing retinal AI fairness or privacy, important considerations for furthering the deployment of ophthalmic AI.…”

Section: Discussionmentioning

confidence: 99%

Detecting Anomalies in Retinal Diseases Using Generative, Discriminative, and Self-supervised Deep Learning

et al. 2022

Self Cite

View full text Add to dashboard Cite

IMPORTANCE Anomaly detectors could be pursued for retinal diagnoses based on artificial intelligence systems that may not have access to training examples for all retinal diseases in all phenotypic presentations. Possible applications could include screening of population for any retinal disease rather than a specific disease such as diabetic retinopathy, detection of novel retinal diseases or novel presentations of common retinal diseases, and detection of rare diseases with little or no data available for training.OBJECTIVE To study the application of anomaly detection to retinal diseases.DESIGN, SETTING, AND PARTICIPANTS High-resolution retinal images from the publicly available EyePACS data set with fundus images with a corresponding label ranging from 0 to 4 for representing different severities of diabetic retinopathy. Sixteen variants of anomaly detectors were designed. For evaluation, a surrogate problem was constructed, using diabetic retinopathy images, in which only retinas with nonreferable diabetic retinopathy, ie, no diabetic macular edema, and no diabetic retinopathy or mild to moderate nonproliferative diabetic retinopathy were used for training an artificial intelligence system, but both nonreferable and referable diabetic retinopathy (including diabetic macular edema or proliferative diabetic retinopathy) were used to test the system for detecting retinal disease. MAIN OUTCOMES AND MEASURESAnomaly detectors were evaluated by commonly accepted performance metrics, including area under the receiver operating characteristic curve, F1 score, and accuracy.RESULTS A total of 88 692 high-resolution retinal images of 44 346 individuals with varying severity of diabetic retinopathy were analyzed. The best performing across all anomaly detectors had an area under the receiver operating characteristic of 0.808 (95% CI, 0.789-0.827) and was obtained using an embedding method that involved a self-supervised network.CONCLUSIONS AND RELEVANCE This study suggests when abnormal (diseased) data, ie, referable diabetic retinopathy in this study, were not available for training of retinal diagnostic systems wherein only nonreferable diabetic retinopathy was used for training, anomaly detection techniques were useful in identifying images with and without referable diabetic retinopathy. This suggests that anomaly detectors may be used to detect retinal diseases in more generalized settings and potentially could play a role in screening of populations for retinal diseases or identifying novel diseases and phenotyping or detecting unusual presentations of common retinal diseases.

show abstract

Section: Discussionmentioning

confidence: 99%

Detecting Anomalies in Retinal Diseases Using Generative, Discriminative, and Self-supervised Deep Learning

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…We summarised these strands of work in Table 2. Synthetically generated graphs can improve the utility of the model trained on this data as well as empirically reduces the effectiveness of inference attacks [90]. There exist several works in the area [9,10,15,56,57,79,92,133] that allow one to generate graph-structured data in a private manner.…”

Section: Local Dp On Graphsmentioning

confidence: 99%

Differentially Private Guarantees for Analytics and Machine Learning on Graphs: A Survey of Results

Mueller,

Usynin,

Paetzold

et al. 2024

JPC

View full text Add to dashboard Cite

We study the applications of differential privacy (DP) in the context of graph-structured data and discuss the formulations of DP applicable to the publication of graphs and their associated statistics as well as machine learning on graph-based data, including graph neural networks (GNNs). Interpreting DP guarantees in the context of graph-structured data can be challenging, as individual data points are interconnected (often non-linearly or sparsely). This connectivity complicates the computation of individual privacy loss in differentially private learning. The problem is exacerbated by an absence of a single, well-established formulation of DP in graph settings. This issue extends to the domain of GNNs, rendering private machine learning on graph-structured data a challenging task. A lack of prior systematisation work motivated us to study graph-based learning from a privacy perspective. In this work, we systematise different formulations of DP on graphs, discuss challenges and promising applications, including the GNN domain. We compare and separate works into graph analytics tasks and graph learning tasks with GNNs. We conclude our work with a discussion of open questions and potential directions for further research in this area.

show abstract

“…The ability to generate synthetic samples allows one to augment existing datasets with additional data points in a privacy-neutral way, resulting in more diverse data representations. This, in turn, improves utility of the model trained on this data as well as empirically reduces the effectiveness of inference attacks [110]. There exist prior works in the area [67,37,26,47,31] that allow to generate graph-structured data in a private manner, however, authors outline a number of limitations.…”

Section: Synthetic Graph Generationmentioning

confidence: 99%

SoK: Differential Privacy on Graph-Structured Data

Mueller¹,

Usynin²,

Paetzold³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this work, we study the applications of differential privacy (DP) in the context of graph-structured data. We discuss the formulations of DP applicable to the publication of graphs and their associated statistics as well as machine learning on graph-based data, including graph neural networks (GNNs). The formulation of DP in the context of graph-structured data is difficult, as individual data points are interconnected (often non-linearly or sparsely). This connectivity complicates the computation of individual privacy loss in differentially private learning. The problem is exacerbated by an absence of a single, well-established formulation of DP in graph settings. This issue extends to the domain of GNNs, rendering private machine learning on graph-structured data a challenging task. A lack of prior systematisation work motivated us to study graph-based learning from a privacy perspective. In this work, we systematise different formulations of DP on graphs, discuss challenges and promising applications, including the GNN domain. We compare and separate works into graph analysis tasks and graph learning tasks with GNNs. Finally, we conclude our work with a discussion of open questions and potential directions for further research in this area.

show abstract

Defending Medical Image Diagnostics Against Privacy Attacks Using Generative Methods: Application to Retinal Diagnostics

Cited by 6 publications

References 25 publications

Detecting Anomalies in Retinal Diseases Using Generative, Discriminative, and Self-supervised Deep Learning

Detecting Anomalies in Retinal Diseases Using Generative, Discriminative, and Self-supervised Deep Learning

Differentially Private Guarantees for Analytics and Machine Learning on Graphs: A Survey of Results

SoK: Differential Privacy on Graph-Structured Data

Contact Info

Product

Resources

About