Federated Learning and Differential Privacy for Medical Image Analysis

Adnan, Mohammed; Kalra, Shivam; Cresswell, Jesse C.; Taylor, Graham W.; Tizhoosh, Hamid R.

doi:10.21203/rs.3.rs-1005694/v1

Cited by 56 publications

(22 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other, more sophisticated methods like the sparse vector technique (SVT) combine the addition of noise with value clipping and/or removal of parts of the data [24]. DP has been successfully integrated into the training of deep neural networks [25]- [27] and used for FL applications [15], [28]- [31]. DP can make strong guarantees about the theoretical effectiveness of protecting against individual privacy loss but is difficult to tune to keep the model accuracy at an acceptable level [32].…”

Section: Differential Privacy (Dp)mentioning

confidence: 99%

Do Gradient Inversion Attacks Make Federated Learning Unsafe?

Hatamizadeh¹,

Yin²,

Molchanov³

et al. 2022

Preprint

View full text Add to dashboard Cite

Federated learning (FL) allows the collaborative training of AI models without needing to share raw data. This capability makes it especially interesting for healthcare applications where patient and data privacy is of utmost concern. However, recent works on the inversion of deep neural networks from model gradients raised concerns about the security of FL in preventing the leakage of training data. In this work, we show that these attacks presented in the literature are impractical in real FL use-cases and provide a new baseline attack that works for more realistic scenarios where the clients' training involves updating the Batch Normalization (BN) statistics. Furthermore, we present new ways to measure and visualize potential data leakage in FL. Our work is a step towards establishing reproducible methods of measuring data leakage in FL and could help determine the optimal tradeoffs between privacy-preserving techniques, such as differential privacy, and model accuracy based on quantifiable metrics.

show abstract

Section: Differential Privacy (Dp)mentioning

confidence: 99%

Do Gradient Inversion Attacks Make Federated Learning Unsafe?

Hatamizadeh¹,

Yin²,

Molchanov³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Differential privacy in federated learning is often achieved using differentially-private stochastic gradient descent (DP-SGD) [7,41,42], an algorithm that determines the appropriate noise scale and how to clip the model parameter. The combination of federated learning and differential privacy has been explored in multiple medical use cases including prediction of mortality and adverse drug reactions from electronic health records [43], brain tumor segmentation [9], classification of pathology whole slide images [20], detection of diabetic retinopathy in images of the retina [44], and identification of lung cancer in histopathologic images [45].…”

Section: Related Workmentioning

confidence: 99%

Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-Ray Data

Ziegler¹,

Pfitzner²,

Schulz³

et al. 2022

Preprint

View full text Add to dashboard Cite

Privacy regulations and the physical distribution of heterogeneous data are often primary concerns for the development of deep learning models in a medical context. This paper evaluates the feasibility of differentially private federated learning for chest X-ray classification as a defense against data privacy attacks. To the best of our knowledge, we are the first to directly compare the impact of differentially private training on two different neural network architectures, DenseNet121 and ResNet50. Extending the federated learning environments previously analyzed in terms of privacy, we simulated a heterogeneous and imbalanced federated setting by distributing images from the public CheXpert and Mendeley chest X-ray datasets unevenly among 36 clients. Both non-private baseline models achieved an area under the receiver operating characteristic curve (AUC) of 0.94 on the binary classification task of detecting the presence of a medical finding. We demonstrate that both model architectures are vulnerable to privacy violation by applying image reconstruction attacks to local model updates from individual clients. The attack was particularly successful during later training stages. To mitigate the risk of privacy breach, we integrated Rényi differential privacy with a Gaussian noise mechanism into local model training. We evaluate model performance and attack vulnerability for privacy budgets ε ∈ {1, 3, 6, 10}. The DenseNet121 achieved the best utility-privacy trade-off with an AUC of 0.94 for ε = 6. Model performance deteriorated slightly for individual clients compared to the non-private baseline. The ResNet50 only reached an AUC of 0.76 in the same privacy setting. Its performance was inferior to that of the DenseNet121 for all considered privacy constraints, suggesting that the DenseNet121 architecture is more robust to differentially private training.

show abstract

“…It accounts for 11.4% of all cancer-related incidence and accounts for 18% of global cancer-related death [185]. Adnan et al [190] studied the effects of IID and non-IID distributions along with the healthcare providers by conducting a case study. They proposed a deferentially private FL framework as the potential solution to analyze histopathology images.…”

Section: F Fl In Medical Image Analysismentioning

confidence: 99%

Federated Learning for Medical Applications: A Taxonomy, Current Trends, Challenges, and Future Research Directions

Rauniyar¹,

Hagos²,

Jha³

et al. 2022

Preprint

View full text Add to dashboard Cite

With the advent of the Internet of Things (IoT), Artificial Intelligence (AI), and Machine Learning (ML)/Deep Learning (DL) algorithms, the data-driven medical application has emerged as a promising tool for designing reliable and scalable diagnostic and prognostic models from medical data. Hence, in recent years, data-driven medical applications have attracted a great deal of attention from academia to industry. This has undoubtedly improved the quality of healthcare delivery. However, AI-based medical applications still have poor adoption due to their difficulties in satisfying strict security, privacy, and quality of service standards such as low latency. Recent developments in Federated Learning (FL) have made it possible to train complex machine-learned models in a distributed manner and has become an active research domain, particularly processing the medical data at the edge of the network in a decentralized way to preserve privacy and address security concerns. To this end, this survey paper highlights the current and future of FL technology in medical applications where data sharing is a significant burden. It also review and discuss the current research trends and their outcomes for designing reliable and scalable FL models. We outline the general FL's statistical problems, device challenges, security, privacy concerns, and its potential in the medical domain. Moreover, our study is also focused on medical applications where we highlight the burden of global cancer and the efficient use of FL for the development of computer-aided diagnosis tools for addressing them. Additionally, the recent literature revealed that FL models ensure a high level of robustness and generalization compared to the traditional data-driven medical applications. We hope that this review serves as a checkpoint that sets forth the existing state-of-the-art works in a thorough manner and offers open problems and future research directions for this field.

show abstract

Federated Learning and Differential Privacy for Medical Image Analysis

Cited by 56 publications

References 21 publications

Do Gradient Inversion Attacks Make Federated Learning Unsafe?

Do Gradient Inversion Attacks Make Federated Learning Unsafe?

Defending against Reconstruction Attacks through Differentially Private Federated Learning for Classification of Heterogeneous Chest X-Ray Data

Federated Learning for Medical Applications: A Taxonomy, Current Trends, Challenges, and Future Research Directions

Contact Info

Product

Resources

About