arXiv subjects

Ee-Chien Chang

Publications and source records attributed to Ee-Chien Chang.

60 records · Page 4Linked to original sources

arXiv2019

Adversarial Neural Network Inversion via Auxiliary Knowledge Alignment

The rise of deep learning technique has raised new privacy concerns about the training data and test data. In this work, we investigate the model inversion problem in the adversarial settings, where the adversary aims at inferring information about the target model's training data and test data from the model's prediction values. We develop a solution to train a second neural network that acts as the inverse of the target model to perform the inversion. The inversion model can be trained with black-box accesses to the target model. We propose two main techniques towards training the inversion model in the adversarial settings. First, we leverage the adversary's background knowledge to compose an auxiliary set to train the inversion model, which does not require access to the original training data. Second, we design a truncation-based technique to align the inversion model to enable effective inversion of the target model from partial predictions that the adversary obtains on victim user's data. We systematically evaluate our inversion approach in various machine learning tasks and model architectures on multiple image datasets. Our experimental results show that even with no full knowledge about the target model's training data, and with only partial prediction values, our inversion approach is still able to perform accurate inversion of the target model, and outperform previous approaches.

cs.CR↗

arXiv2018

Fair Marketplace for Secure Outsourced Computations

The cloud computing paradigm offers clients ubiquitous and on demand access to a shared pool of computing resources, enabling the clients to provision scalable services with minimal management effort. Such a pool of resources, however, is typically owned and controlled by a single service provider, making it a single-point-of-failure. This paper presents Kosto - a framework that provisions a fair marketplace for secure outsourced computations, wherein the pool of computing resources aggregates resources offered by a large cohort of independent compute nodes. Kosto protects the confidentiality of clients' inputs as well as the integrity of the outsourced computations and their results using trusted hardware's enclave execution, in particular Intel SGX. Furthermore, Kosto warrants fair exchanges between the clients' payments for the execution of an outsourced computations and the compute nodes' work in servicing the clients' requests. Empirical evaluation on the prototype implementation of Kosto shows that performance overhead incurred by enclave execution is as small as 3% for computation-intensive operations, and 1.5x for IO-intensive operations.

cs.CR↗

arXiv2018

Flipped-Adversarial AutoEncoders

We propose a flipped-Adversarial AutoEncoder (FAAE) that simultaneously trains a generative model G that maps an arbitrary latent code distribution to a data distribution and an encoder E that embodies an "inverse mapping" that encodes a data sample into a latent code vector. Unlike previous hybrid approaches that leverage adversarial training criterion in constructing autoencoders, FAAE minimizes re-encoding errors in the latent space and exploits adversarial criterion in the data space. Experimental evaluations demonstrate that the proposed framework produces sharper reconstructed images while at the same time enabling inference that captures rich semantic representation of data.

cs.LG↗

arXiv2017

Evading Classifiers by Morphing in the Dark

Learning-based systems have been shown to be vulnerable to evasion through adversarial data manipulation. These attacks have been studied under assumptions that the adversary has certain knowledge of either the target model internals, its training dataset or at least classification scores it assigns to input samples. In this paper, we investigate a much more constrained and realistic attack scenario wherein the target classifier is minimally exposed to the adversary, revealing on its final classification decision (e.g., reject or accept an input sample). Moreover, the adversary can only manipulate malicious samples using a blackbox morpher. That is, the adversary has to evade the target classifier by morphing malicious samples "in the dark". We present a scoring mechanism that can assign a real-value score which reflects evasion progress to each sample based on the limited information available. Leveraging on such scoring mechanism, we propose an evasion method -- EvadeHC -- and evaluate it against two PDF malware detectors, namely PDFRate and Hidost. The experimental evaluation demonstrates that the proposed evasion attacks are effective, attaining $100\%$ evasion rate on the evaluation dataset. Interestingly, EvadeHC outperforms the known classifier evasion technique that operates based on classification scores output by the classifiers. Although our evaluations are conducted on PDF malware classifier, the proposed approaches are domain-agnostic and is of wider application to other learning-based systems.

cs.CR↗

arXiv2011

Publishing Location Dataset Differential Privately with Isotonic Regression

We consider the problem of publishing location datasets, in particular 2D spatial pointsets, in a differentially private manner. Many existing mechanisms focus on frequency counts of the points in some a priori partition of the domain that is difficult to determine. We propose an approach that adds noise directly to the point, or to a group of neighboring points. Our approach is based on the observation that, the sensitivity of sorting, as a function on sets of real numbers, can be bounded. Together with isotonic regression, the dataset can be accurately reconstructed. To extend the mechanism to higher dimension, we employ locality preserving function to map the dataset to a bounded interval. Although there are fundamental limits on the performance of locality preserving functions, fortunately, our problem only requires distance preservation in the "easier" direction, and the well-known Hilbert space-filling curve suffices to provide high accuracy. The publishing process is simple from the publisher's point of view: the publisher just needs to map the data, sort them, group them, add Laplace noise and publish the dataset. The only parameter to determine is the group size which can be chosen based on predicted generalization errors. Empirical study shows that the published dataset can also exploited to answer other queries, for example, range query and median query, accurately.

cs.CR↗

arXiv2010

Securing Interactive Sessions Using Mobile Device through Visual Channel and Visual Inspection

Communication channel established from a display to a device's camera is known as visual channel, and it is helpful in securing key exchange protocol. In this paper, we study how visual channel can be exploited by a network terminal and mobile device to jointly verify information in an interactive session, and how such information can be jointly presented in a user-friendly manner, taking into account that the mobile device can only capture and display a small region, and the user may only want to authenticate selective regions-of-interests. Motivated by applications in Kiosk computing and multi-factor authentication, we consider three security models: (1) the mobile device is trusted, (2) at most one of the terminal or the mobile device is dishonest, and (3) both the terminal and device are dishonest but they do not collude or communicate. We give two protocols and investigate them under the abovementioned models. We point out a form of replay attack that renders some other straightforward implementations cumbersome to use. To enhance user-friendliness, we propose a solution using visual cues embedded into the 2D barcodes and incorporate the framework of "augmented reality" for easy verifications through visual inspection. We give a proof-of-concept implementation to show that our scheme is feasible in practice.

cs.CR↗