Lalitha Sankar

Lalitha Sankar


Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 December 2017 in Entropy
Verified
Journal Article
Open access
PDF file
CHChong Huang
Chong Huang
PKPeter Kairouz
Peter Kairouz
XCXiao Chen
Xiao Chen
LSLalitha Sankar
Lalitha Sankar
RRRam Rajagopal
Ram Rajagopal
Preserving the utility of published datasets while simultaneously providing provable privacy guarantees is a well-known challenge. On the one hand, context-free privacy solutions, such as differential privacy, provide strong privacy guarantees, but often lead to a significant reduction in utility. On the other hand, context-aware privacy solutions, such as information theoretic privacy, achieve an improved privacy-utility tradeoff, but assume that the data holder has access to dataset statistics. We circumvent these limitations by introducing a novel context-aware privacy framework called generative adversarial privacy (GAP). GAP leverages recent advancements in generative adversarial networks (GANs) to allow the data holder to learn privatization schemes from the dataset itself. Under GAP, learning the privacy mechanism is formulated as a constrained minimax game between two players: a privatizer that sanitizes the dataset in a way that limits the risk of inference attacks on the individuals’ private variables, and an adversary that tries to infer the private variables from the sanitized dataset. To evaluate GAP’s performance, we investigate two simple (yet canonical) statistical dataset models: (a) the binary data model; and (b) the binary Gaussian mixture model. For both models, we derive game-theoretically optimal minimax privacy mechanisms, and show that the privacy mechanisms learned from data (in a generative adversarial fashion) match the theoretically optimal ones. This demonstrates that our framework can be easily applied in practice, even in the absence of dataset statistics.

17 March 2021 in IEEE Journal on Selected Areas in Information Theory
Verified
Journal Article
Closed access
MBMatthieu Bloch
Matthieu Bloch
Onur GünlüOnur Günlü
Onur Günlü
AYAylin Yener
Aylin Yener
FOFrederique Oggier
Frederique Oggier
H. Vincent PoorH. Vincent Poor
H. Vincent Poor
RSRafael F. Schaefer
Rafael F. Schaefer
This tutorial reviews fundamental contributions to information security. An integrative viewpoint is taken that explains the security metrics, including secrecy, privacy, and others, the methodology of information-theoretic approaches, along with the arising system design principles, as well as techniques that enable the information-theoretic designs to be applied in real communication and computing systems. The tutorial, while summarizing these contributions, argues for the simultaneous pivotal role of fundamental limits and coding techniques for secure communication system design.

16 August 2019 in IEEE Transactions on Information Theory
Verified
Journal Article
Closed access
JLJiachun Liao
Jiachun Liao
OKOliver Kosut
Oliver Kosut
LSLalitha Sankar
Lalitha Sankar
FCFlavio Du Pin Calmon
Flavio Du Pin Calmon
We introduce a tunable measure for information leakage called maximal $\alpha $ -leakage . This measure quantifies the maximal gain of an adversary in inferring any (potentially random) function of a dataset from a release of the data. The inferential capability of the adversary is, in turn, quantified by a class of adversarial loss functions that we introduce as $\alpha $ -loss, $\alpha \in [1,\infty) \cup \{\infty \}$ . The choice of $\alpha $ determines the specific adversarial action and ranges from refining a belief (about any function of the data) for $\alpha =1$ to guessing the most likely value for $\alpha = \infty $ while refining the $\alpha ^{\text {th}}$ moment of the belief for $\alpha $ in between. Maximal $\alpha $ -leakage then quantifies the adversarial gain under $\alpha $ -loss over all possible functions of the data. In particular, for the extremal values of $\alpha =1$ and $\alpha =\infty $ , maximal $\alpha $ -leakage simplifies to mutual information and maximal leakage, respectively. For $\alpha \in (1,\infty)$ this measure is shown to be the Arimoto channel capacity of order $\alpha $ . We show that maximal $\alpha $ -leakage satisfies data processing inequalities and a sub-additivity property thereby allowing for a weak composition result. Building upon these properties, we use maximal $\alpha $ -leakage as the privacy measure and study the problem of data publishing with privacy guarantees, wherein the utility of the released data is ensured via a hard distortion constraint. Unlike average distortion, hard distortion provides a deterministic guarantee of fidelity. We show that under a hard distortion constraint, for $\alpha >1$ the optimal mechanism is independent of $\alpha $ , and therefore, the resulting optimal tradeoff is the same for all values of $\alpha >1$ . Finally, the tunability of maximal $\alpha $ -leakage as a privacy measure is also illustrated for binary data with average Hamming distortion as the utility measure.

23 March 2018 in IEEE Transactions on Power Systems
Verified
Journal Article
Closed access
JZJiazi Zhang
Jiazi Zhang
ZCZhigang Chu
Zhigang Chu
LSLalitha Sankar
Lalitha Sankar
OKOliver Kosut
Oliver Kosut
This paper studies physical consequences of unobservable false data injection (FDI) attacks designed only with information inside a subnetwork of the power system. The goal of this attack is to overload a chosen target line without being detected via measurements. To overcome the limited information, a multiple linear regression model is developed to learn the relationship between the external network and the attack subnetwork from historical data. The worst possible consequences of such FDI attacks are evaluated by solving a bi-level optimization problem wherein the first level models the limited attack resources, while the second level formulates the system response to such attacks via dc optimal power flow (OPF). The attack model with limited information is reflected in the dc OPF formulation that only takes into account the system information for the attack subnetwork. The vulnerability of this attack model is illustrated on the IEEE 24-bus reliability test system and the IEEE 118-bus systems.

1 December 2017 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Open access
JLJiachun Liao
Jiachun Liao
LSLalitha Sankar
Lalitha Sankar
VTVincent Tan
Vincent Tan
FCFlavio Du Pin Calmon
Flavio Du Pin Calmon
Hypothesis testing is a statistical inference framework for determining the true distribution among a set of possible distributions for a given dataset. Privacy restrictions may require the curator of the data or the respondents themselves to share data with the test only after applying a randomizing privacy mechanism. This work considers mutual information (MI) as the privacy metric for measuring leakage. In addition, motivated by the Chernoff-Stein lemma, the relative entropy between pairs of distributions of the output (generated by the privacy mechanism) is chosen as the utility metric. For these metrics, the goal is to find the optimal privacy-utility trade-off (PUT) and the corresponding optimal privacy mechanism for both binary and m-ary hypothesis testing. Focusing on the high privacy regime, Euclidean information-theoretic approximations of the binary and m-ary PUT problems are developed. The solutions for the approximation problems clarify that an MI-based privacy metric preserves the privacy of the source symbols in inverse proportion to their likelihoods.

5 September 2019 in IEEE Transactions on Information Theory
Verified
Journal Article
Closed access
MDMario Diaz
Mario Diaz
HWHao Wang
Hao Wang
FCFlavio Du Pin Calmon
Flavio Du Pin Calmon
LSLalitha Sankar
Lalitha Sankar
Consider a data publishing setting for a dataset composed by both private and non-private features. The publisher uses an empirical distribution, estimated from $n$ i.i.d. samples, to design a privacy mechanism which is applied to new fresh samples afterward. In this paper, we study the discrepancy between the privacy-utility guarantees for the empirical distribution, used to design the privacy mechanism, and those for the true distribution, experienced by the privacy mechanism in practice. We first show that, for any privacy mechanism, these discrepancies vanish at speed $O(1/\sqrt {n})$ with high probability. These bounds follow from our main technical results regarding the Lipschitz continuity of the considered information leakage measures. Then we prove that the optimal privacy mechanisms for the empirical distribution approach the corresponding mechanisms for the true distribution as the sample size $n$ increases, thereby establishing the statistical consistency of the optimal privacy mechanisms. Finally, we introduce and study uniform privacy mechanisms which, by construction, provide privacy to all the distributions within a neighborhood of the estimated distribution and, thereby, guarantee privacy for the true distribution with high probability.