Publications

Forthcoming
Kung, S. Y., et al.Collaborative PCA/DCA Learning Methods for Compressive Privacy”. ACM Transaction in Embedded Computing Systems (Forthcoming). Web. Authors' VersionAbstract

In the internet era, the data being collected on consumers like us are growing exponentially and attacks on our privacy are becoming a real threat. To better assure our privacy, it is safer to let data owner control the data to be uploaded to the network, as opposed to taking chance with the data servers or the third parties. To this end, we propose a privacy-preserving technique, named Compressive Privacy (CP), to enable the data creator to compress data via collaborative learning, so that the compressed data uploaded onto the internet will be useful only for the intended utility and will not be easily diverted to malicious applications.

For data in a high-dimensional feature vector space, a common approach to data compression is dimension reduction or, equivalently, subspace projection. The most prominent tool is Principal Component Analysis (PCA). For unsupervised learning, PCA can best recover the original data given a specific reduced dimensionality. However, for supervised learning environment, it is more effective to adopt a supervised PCA, known as the Discriminant Component Analysis (DCA), in order to maximize the discriminant capability.

The DCA subspace analysis embraces two different subspaces. The signal subspace components of DCA are associated with the discriminant distance/power (related to the classification effectiveness), while the noise subspace components of DCA are tightly coupled with the recoverability and/or privacy protection. This paper will present three DCA-related data compression methods useful for privacy-preserving applications.

  • Utility-driven DCA: Because the rank of the signal subspace is limited by the number of classes, DCA can effectively support classification using a relatively small dimensionality (i.e. high compression).
  • Desensitized PCA: By incorporating a signal-subspace ridge into DCA, it leads to a variant especially effective for extracting privacy-preserving components. In this case, the eigenvalues of the noise-space are made to become insensitive to the privacy labels and are ordered according to their corresponding component powers.
  • Desensitized K-means/SOM: Since the revelation of the K-means or SOM cluster structure could leak sensitive information, it will be safer perform K-means or SOM clustering on desensitized PCA subspace.
2016
Chanyaswad, Thee, et al.Discriminant-component eigenfaces for privacy-preserving face recognition”. 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP) 2016. Web. Publisher's VersionAbstract

Over the past decades, face recognition has been a problem of critical interest in the machine learning and signal processing communities. However, conventional approaches such as eigenfaces do not protect the privacy of user data, which is emerging as an important design consideration in today's society. In this work, we leverage a supervised-learning subspace projection method called Discriminant Component Analysis (DCA) for privacy-preserving face recognition. By projecting the data onto the lower-dimensional signal subspace prescribed by DCA, high performance of face recognition is achievable without compromising privacy of the data owners. We evaluate our approach on three image datasets: Yale, Olivetti and Glasses datasets - the last is derived from the former two. Our approach can serve as a key enabler for real-world deployment of privacy-preserving face recognition applications, and provides a promising direction to researchers and private sectors.

2012
Kulkarni, Vishwesh V, et al.Robust tunable in vitro transcriptional oscillator networks”. 50th Annual Allerton Conference on Communication, Control, and Computing 2012114--119. Web. Publisher's VersionAbstract

Synthetic biology is facilitating novel methods and components to build in vivo and in vitro circuits to better understand and re-engineer biological networks. Circadian oscillators serve as molecular clocks that govern several important cellular processes such as cell division and apoptosis. Hence, successful demonstration of synthetic oscillators have become a primary design target for many synthetic biology endeavors. Recently, three synthetic transcriptional oscillators were demonstrated by Kim and Winfree utilizing modular architecture of synthetic gene analogues and a few enzymes. However, the periods and amplitudes of synthetic oscillators were sensitive to initial conditions and allowed limited tunability. In addition, it being a closed system, the oscillations were observe to die out after a certain period of time. To increase tunability and robustness of synthetic biochemical oscillators in the face of disturbances and modeling uncertainties, a control theoretic approach for real-time adjustment of oscillator behaviors would be required. In this paper, assuming an open system implementation is feasible, we demonstrate how dynamic inversion techniques can be used to synthesize the required controllers.