Towards internal privacy and flexible K-anonymity

Hellani, Hussein; Kilany, Rima; Sokhn, Maria

doi:10.1109/arcse.2015.7338148

Cited by 3 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different techniques have been developed to protect data and model privacy during the training and in the subsequent inference phase. Anonymisation techniques [e.g., K-anonymity (Hellani et al, 2015 )] were among the first approaches developed to ensure privacy in model training. Meanwhile, there have been outstanding breakthroughs in the area of privacy attacks.…”

Section: Related Workmentioning

confidence: 99%

The privacy-explainability trade-off: unraveling the impacts of differential privacy and federated learning on attribution methods

Saifullah,

Mercier,

Lucieri

et al. 2024

Front. Artif. Intell.

View full text Add to dashboard Cite

Since the advent of deep learning (DL), the field has witnessed a continuous stream of innovations. However, the translation of these advancements into practical applications has not kept pace, particularly in safety-critical domains where artificial intelligence (AI) must meet stringent regulatory and ethical standards. This is underscored by the ongoing research in eXplainable AI (XAI) and privacy-preserving machine learning (PPML), which seek to address some limitations associated with these opaque and data-intensive models. Despite brisk research activity in both fields, little attention has been paid to their interaction. This work is the first to thoroughly investigate the effects of privacy-preserving techniques on explanations generated by common XAI methods for DL models. A detailed experimental analysis is conducted to quantify the impact of private training on the explanations provided by DL models, applied to six image datasets and five time series datasets across various domains. The analysis comprises three privacy techniques, nine XAI methods, and seven model architectures. The findings suggest non-negligible changes in explanations through the implementation of privacy measures. Apart from reporting individual effects of PPML on XAI, the paper gives clear recommendations for the choice of techniques in real applications. By unveiling the interdependencies of these pivotal technologies, this research marks an initial step toward resolving the challenges that hinder the deployment of AI in safety-critical settings.

show abstract

Section: Related Workmentioning

confidence: 99%

The privacy-explainability trade-off: unraveling the impacts of differential privacy and federated learning on attribution methods

Saifullah,

Mercier,

Lucieri

et al. 2024

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…A constrained version of k -Anonymity was later proposed by Miller et al [ 14 ] and refined by Campan et al [ 15 ] with the p -Sensitive k -Anonymity model, which limits the amount of allowed generalization when masking microdata. Recently, new extensions focusing on flexible k -Anonymity were proposed in [ 16 , 17 ] to enable the deployment of k -Anonymity to other application scenarios by defining a semantic ontology to generate suitable k -blocks of data.…”

Section: Background and Related Workmentioning

confidence: 99%

k-Same-Net: k-Anonymity with Generative Deep Neural Networks for Face Deidentification

Meden

Emeršič

Štruc

et al. 2018

Entropy

View full text Add to dashboard Cite

; Tel.: +386-1-479-8245 † This paper is an extended version of our paper published in Meden B.; Emeršič Ž.; Štruc V.; Peer P.k-Same-Net: Neural-Network-Based Face Deidentification. In the Proceedings of the International Conference and Workshop on Bioinspired Intelligence (IWOBI), Funchal Madeira, Portugal, 10-12 July 2017.Received: 1 December 2017 ; Accepted: 9 January 2018; Published: 13 January 2018Abstract: Image and video data are today being shared between government entities and other relevant stakeholders on a regular basis and require careful handling of the personal information contained therein. A popular approach to ensure privacy protection in such data is the use of deidentification techniques, which aim at concealing the identity of individuals in the imagery while still preserving certain aspects of the data after deidentification. In this work, we propose a novel approach towards face deidentification, called k-Same-Net, which combines recent Generative Neural Networks (GNNs) with the well-known k-Anonymitymechanism and provides formal guarantees regarding privacy protection on a closed set of identities. Our GNN is able to generate synthetic surrogate face images for deidentification by seamlessly combining features of identities used to train the GNN model. Furthermore, it allows us to control the image-generation process with a small set of appearance-related parameters that can be used to alter specific aspects (e.g., facial expressions, age, gender) of the synthesized surrogate images. We demonstrate the feasibility of k-Same-Net in comprehensive experiments on the XM2VTS and CK+ datasets. We evaluate the efficacy of the proposed approach through reidentification experiments with recent recognition models and compare our results with competing deidentification techniques from the literature. We also present facial expression recognition experiments to demonstrate the utility-preservation capabilities of k-Same-Net.Our experimental results suggest that k-Same-Net is a viable option for facial deidentification that exhibits several desirable characteristics when compared to existing solutions in this area.

show abstract

Object detection under the lens of privacy: A critical survey of methods, challenges, and future directions

Moon,

Bukhari,

Kim

et al. 2024

ICT Express

View full text Add to dashboard Cite

Towards internal privacy and flexible K-anonymity

Cited by 3 publications

References 5 publications

The privacy-explainability trade-off: unraveling the impacts of differential privacy and federated learning on attribution methods

The privacy-explainability trade-off: unraveling the impacts of differential privacy and federated learning on attribution methods

k-Same-Net: k-Anonymity with Generative Deep Neural Networks for Face Deidentification

Object detection under the lens of privacy: A critical survey of methods, challenges, and future directions

Contact Info

Product

Resources

About