Known Sample Attacks on Relation Preserving Data Transformations

Kaplan, Emre; Gürsoy, Mehmet Emre; Nergiz, Mehmet Ercan; Saygın, Yücel

doi:10.1109/tdsc.2017.2759732

Cited by 13 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kaplan et al [16] propose a SA scheme by utilizing the relation of multiple compromised transformed templates from the same individual. The scheme exploits distance preserving trait of the transformation algorithm.…”

Section: Related Work 21 Similarity-based Attack (Sa)mentioning

confidence: 99%

Interpretable security analysis of cancellable biometrics using constrained-optimized similarity-based attack

Wang

Dong

Jin

et al. 2021

2021 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW)

View full text Add to dashboard Cite

Cancellable biometrics (CB) intentionally distorts biometric template for security protection, and simultaneously preserving the distance/similarity for matching in the transformed domain. Despite its effectiveness, the security issues attributed to similarity preservation property of CB is underestimated. Dong et al. [BTAS'19], exploited the similarity preservation trait of CB and proposed a similarity-based attack with high successful attack rate. The similarity-based attack utilizes preimage that generated from the protected biometric template for impersonation and perform cross matching. In this paper, we propose a constrained optimization similarity-based attack (CSA), which is improved upon Dong's genetic algorithm enabled similarity-based attack (GASA). The CSA applies algorithm-specific equality or inequality relations as constraints, to optimize preimage generation. We justify the effectiveness of CSA from the supervised learning perspective. We conduct extensive experiments to demonstrate CSA against Index-of-Max (IoM) hashing with LFW face dataset. The results suggest that CSA is effective to breach IoM hashing security, and outperforms GASA remarkably. Furthermore, we reveal the correlation of IoM hash code size and the attack performance of CSA.

show abstract

Section: Related Work 21 Similarity-based Attack (Sa)mentioning

confidence: 99%

Interpretable security analysis of cancellable biometrics using constrained-optimized similarity-based attack

Wang

Dong

Jin

et al. 2021

2021 IEEE Winter Conference on Applications of Computer Vision Workshops (WACVW)

View full text Add to dashboard Cite

show abstract

“…A recent work [17] has devised an attack on Relation Preserving Transformation (RPT). Since RPT is the basis of our transformation, it may be open to breach by [17].…”

Section: Number Of Iterations Needed To Convergementioning

confidence: 99%

“…A recent work [17] has devised an attack on Relation Preserving Transformation (RPT). Since RPT is the basis of our transformation, it may be open to breach by [17]. Assuming that such an attack is implemented, we analyze the feasibility of it in detail.…”

Section: Number Of Iterations Needed To Convergementioning

confidence: 99%

“…We first recall the salient features of the attack proposed in [17]. It is assumed that there exists a third party malicious adversary and the attacker has knowledge about some original data points.…”

Section: Number Of Iterations Needed To Convergementioning

confidence: 99%

“…As per [17], the complexity of their algorithm is O( |K| 2 ( R c ) d I). In the above expression, |K| is the size of known sample, R is the range of data points, c the length of a cell into which the entire space is divided and I is the complexity of finding Intersection.…”

Section: Number Of Iterations Needed To Convergementioning

confidence: 99%

See 2 more Smart Citations

Privacy Preserving Multi-server k-means Computation over Horizontally Partitioned Data

Ghosal

Chatterjee

2018

Information Systems Security

View full text Add to dashboard Cite

The k-means clustering is one of the most popular clustering algorithms in data mining. Recently a lot of research has been concentrated on the algorithm when the data-set is divided into multiple parties or when the data-set is too large to be handled by the data owner. In the latter case, usually some servers are hired to perform the task of clustering. The data set is divided by the data owner among the servers who together compute the k-means and return the cluster labels to the owner. The major challenge in this method is to prevent the servers from gaining substantial information about the actual data of the owner. Several algorithms have been designed in the past that provide cryptographic solutions to perform privacy preserving k-means. We propose a new method to perform k-means over a large set of data using multiple servers. Our technique avoids heavy cryptographic computations and instead we use a simple randomization technique to preserve the privacy of the data. The k-means computed has essentially the same efficiency and accuracy as the k-means computed over the original data-set without any randomization. We argue that our algorithm is secure against honest-but-curious and and non-colluding adversary.

show abstract

Masquerade attack on biometric hashing via BiohashGAN

Zhang-yong

Wan

et al. 2021

Vis Comput

View full text Add to dashboard Cite

Known Sample Attacks on Relation Preserving Data Transformations

Cited by 13 publications

References 15 publications

Interpretable security analysis of cancellable biometrics using constrained-optimized similarity-based attack

Interpretable security analysis of cancellable biometrics using constrained-optimized similarity-based attack

Privacy Preserving Multi-server k-means Computation over Horizontally Partitioned Data

Masquerade attack on biometric hashing via BiohashGAN

Contact Info

Product

Resources

About