Image Feature Extraction in Encrypted Domain With Privacy-Preserving SIFT

Hsu, Chao-Yung; Lu, Chun-Shien; Pei, Soo‐Chang

doi:10.1109/tip.2012.2204272

Cited by 186 publications

(14 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A method for security feature of SIFT is proposed in [59]. The authors proposed privacy preserving SIFT to solve the problem of feature extraction in encrypted domain.…”

Section: Measures For Security Specific To Untrusted Server and Imagementioning

confidence: 99%

“…Distributed agent-based privacy-preserving framework Privacy preservation for Untrusted Server [56] Identity-based Encryption Security [57] Grouper framework without trusted central servers Security [58] Privacy preserving SIFT Image Feature Extraction with Privacy preservation [59] Securing SIFT Image Feature Extraction with Privacy preservation [60]…”

Section: Proposed Work Focus Referencesmentioning

confidence: 99%

“…Privacy preservation record linkage, trust based mechanism, Multifactor authentication, dynamic programming, role based multitenancy access control, ant colony optimization [16], [17], [18], [19], [20], [21], [22], [23] [24], [25], [27], [31], [33], [35], [36], [38], [39], [44], [46], [58], [59], [60]. [21], [22], [26], [27], [36], [37], [38], [40], [42], [43], [44], [45] Vendor Lock-In Lack of Interoperability, technical incompatibilities, cost, complexity, lack of portability, Legal Constraints Standardization of API , Fragmentation., horizontal and vertical integration.…”

Section: Data Privacy Authentication Data Protection Eavesdroppingmentioning

confidence: 99%

See 2 more Smart Citations

An Exhaustive Review on Security Issues in Cloud Computing

Fatima¹,

Ahmad²

2019

KSII TIIS

View full text Add to dashboard Cite

The Cloud Computing is growing rapidly in the current IT industry. Cloud computing has become a buzzword in relation to Grid & Utility computing. It provides on demand services to customers and customers will pay for what they get. Various "Cloud Service Provider" such as Microsoft Azure, Google Web Services etc. enables the users to access the cloud in cost effective manner. However, security, privacy and integrity of data is a major concern. In this paper various security challenges have been identified and the survey briefs the comprehensive overview of various security issues in cloud computing. The classification of security issues in cloud computing have been studied. In this paper we have discussed security challenges in cloud computing and also list recommended methods available for addressing them in the literature.

show abstract

“…A method for security feature of SIFT is proposed in [59]. The authors proposed privacy preserving SIFT to solve the problem of feature extraction in encrypted domain.…”

Section: Measures For Security Specific To Untrusted Server and Imagementioning

confidence: 99%

Section: Proposed Work Focus Referencesmentioning

confidence: 99%

Section: Data Privacy Authentication Data Protection Eavesdroppingmentioning

confidence: 99%

See 1 more Smart Citation

An Exhaustive Review on Security Issues in Cloud Computing

Fatima¹,

Ahmad²

2019

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…SecSIFT [53] employed orderpreserving encryption and distributes the SIFT computation among different servers. Hsu et al [27] proposed a privacy preserving SIFT based on homomorphic encryption, while Bai et al [7] performed SURF feature extraction in encrypted domain using Paillier's homomorphic cryptosystem. Wang et al [70] improve the SURF algorithm in encrypted domain by designing protocols for secure multiplication and comparison, that employ a "somewhat" homomorphic encryption.…”

Section: Privacy Preserving Image Matchingmentioning

confidence: 99%

A Secure Mobile Authentication Alternative to Biometrics

Azimpourkivi

Topkara

Cărbunar

2017

Proceedings of the 33rd Annual Computer Security Applications Conference

View full text Add to dashboard Cite

Biometrics are widely used for authentication in consumer devices and business se ings as they provide sufficiently strong security, instant verification and convenience for users. However, biometrics are hard to keep secret, stolen biometrics pose lifelong security risks to users as they cannot be reset and re-issued, and transactions authenticated by biometrics across different systems are linkable and traceable back to the individual identity. In addition, their cost-benefit analysis does not include personal implications to users, who are least prepared for the imminent negative outcomes, and are not o en given equally convenient alternative authentication options.We introduce ai.lock, a secret image based authentication method for mobile devices which uses an imaging sensor to reliably extract authentication credentials similar to biometrics. Despite lacking the regularities of biometric image features, we show that ai.lock consistently extracts features across authentication a empts from general user captured images, to reconstruct credentials that can match and exceed the security of biometrics (EER = 0.71%). ai.lock only stores a "hash" of the object's image. We measure the security of ai.lock against brute force a acks on more than 3.5 billion authentication instances built from more than 250,000 images of real objects, and 100,000 synthetically generated images using a generative adversarial network trained on object images. We show that the ai.lock Shannon entropy is superior to a fingerprint based authentication built into popular mobile devices.

show abstract

“…Afterward, a privacy-protection image search method that utilizes homomorphic encryption presented by Hsu et al [19]. In spite of perceiving images with high precision, this plan is two to four requests of-size more costly, and requested the standard inclusion of the client all through the searching procedure.…”

Section: Introductionmentioning

confidence: 99%

EEIRI: Efficient Encrypted Image Retrieval in IoT-Cloud

2019

KSII TIIS

View full text Add to dashboard Cite

One of the best means to safeguard the confidentiality, security, and privacy of an image within the IoT-Cloud is through encryption. However, looking through encrypted data is a difficult process. Several techniques for searching encrypted data have been devised, but certain security solutions may not be used in IoT-Cloud because such solutions are not lightweight. We propose a lightweight scheme that can perform a content-based search of encrypted images, namely EEIRI. In this scheme, the images are represented using local features. We develop and validate a secure scheme for measuring the Euclidean distance between two descriptor sets. To improve the search efficiency, we employ the k-means clustering technique to construct a searchable tree-based index. Our index construction process ensures the privacy of the stored data and search requests. When compared with more familiar techniques of searching images over plaintexts, EEIRI is considered to be more efficient, demonstrating a higher search cost of 7% and a decrease in search accuracy of 1.7%. Numerous empirical investigations are carried out in relation to real image collections so as to evidence our work.

show abstract

Image Feature Extraction in Encrypted Domain With Privacy-Preserving SIFT

Cited by 186 publications

References 31 publications

An Exhaustive Review on Security Issues in Cloud Computing

An Exhaustive Review on Security Issues in Cloud Computing

A Secure Mobile Authentication Alternative to Biometrics

EEIRI: Efficient Encrypted Image Retrieval in IoT-Cloud

Contact Info

Product

Resources

About