SANER 2019 Workshops
Workshops of the 2019 IEEE 26th International Conference on Software Analysis, Evolution, and Reengineering (SANER)
Powered by
Conference Publishing Consulting

2019 IEEE 1st International Workshop on Artificial Intelligence for Mobile (AI4Mobile), February 24, 2019, Hangzhou, China

AI4Mobile 2019 – Advance Table of Contents

Contents - Abstracts - Authors

2019 IEEE 1st International Workshop on Artificial Intelligence for Mobile (AI4Mobile)


Title Page

Message from the Chairs
Welcome to the IEEE 1st International Workshop on Artificial Intelligence for Mobile (AI4Mobile), held on February 24, 2019, co-located with the IEEE 26th International Conference on Software Analysis, Evolution, and Reengineering (SANER) in Hangzhou, China. The main objective of this workshop is to bring together international researchers and practitioners in the field of both artificial intelligence and mobile app analysis to exchange and discuss the most recent synergistic artificial intelligence for mobile applications, systems, and security.

Mobile Applications and AI

A Mobile Application for Tree Classification and Canopy Calculation using Machine Learning
Kangyi Wang, Yunjie Jia, Ruixi Huo, and Richard Sinnott
(University of Melbourne, Australia)
This paper presents a novel application of machine learning through a mobile application that is used to address the requirements of hobby horticulturists through to the agricultural industry. Specifically, many large-scale farms such as fruit grow-ers require information on the amount of chemicals, e.g. pesti-cides, to use on their crops. Hitherto, this is based on approxi-mate estimates of the size of their fruit trees, where size here equates to the volume of their canopy and hence the amount of leaves that need to be sprayed. In this paper we present an ap-proach to overcome such approximate measures through the development of a mobile phone-based application used to calcu-late the volume more accurately. For the hobby horticulturalist, the type of tree is also established using photographs of the tree and leaves.
Article Search
A Mobile Application for Cat Detection and Breed Recognition Based on Deep Learning
Xiaolu Zhang, Luyang Yang, and Richard Sinnott
(University of Melbourne, Australia)
Deep learning is one of the latest technologies in computer science. It allows using machines to solve problems in a manner similar to the human brain. Deep learning approaches have significantly improved the performance of visual recognition applications including image classification and image detection. In this paper we benchmark different deep learning models and present an Android application used to predict the location and breed of a given cat using a mobile phone camera. The average accuracy of the finalized model was 81.74%.
Article Search
Automated Cross-Platform GUI Code Generation for Mobile Apps
Sen Chen, Lingling Fan, Ting Su, Lei Ma, Yang Liu, and Lihua Xu
(Nanyang Technological University, Singapore; Harbin Institute of Technology, China; NYU Shanghai, China)
Android and iOS are the two dominant platforms for building mobile apps. To provide uniform and smooth user experience, app companies typically employ two teams of programmers to develop UIs (and underlying functionalities) for these two platforms, respectively. However, this development practice is costly for both development and maintenance. To reduce the cost, we take the first step in this direction by proposing an automated cross-platform GUI code generation framework. It can transfer the GUI code implementation between the two mobile platforms. Specifically, our framework takes as input the UI pages and outputs the GUI code for the target platform (e.g., Android or iOS). It contains three phases, i.e., component identification, component type mapping, and GUI code generation. It leverages image processing and deep learning classification techniques. Apart from the UI pages of an app, this framework does not require any other inputs, which makes it possible for large-scale, platform-independent code generation.
Article Search

Mobile Malware and AI

Adversarial Attacks on Mobile Malware Detection
Maryam Shahpasand, Len Hamey, Dinusha Vatsalan, and Minhui Xue
(Macquarie University, Australia; Data61 at CSIRO, Australia)

In recent years, machine learning approaches have been widely adopted for computer security tasks, including malware detection. Malware is a potent threat and an ongoing issue especially on smartphones which account for more than half of global web traffic. Although detection solutions are improving with the advances in machine learning techniques, they have been shown to be vulnerable to adversarial samples that carefully crafted perturbation enables them to evade detection. We propose a machine learning based model to attack malware classifiers leveraging the expressive capability of generative adversarial networks (GANs). We use GANs to generate effective adversarial samples by implying a threshold on the distortion amount on the generated samples. We show that the generated samples can bypass detection in 99% of attempts using a real Android application dataset.

Article Search
How Can We Craft Large-Scale Android Malware? An Automated Poisoning Attack
Sen Chen, Minhui Xue, Lingling Fan, Lei Ma, Yang Liu, and Lihua Xu
(Nanyang Technological University, Singapore; Macquarie University, Australia; Harbin Institute of Technology, China; NYU Shanghai, China)
Android malware, is one of the most serious threats to mobile security. Today, machine learning-based approach is one of the most promising approaches in detecting Android malware. However, our previous experiments show that sophisticated attackers can craft large-scale Android malware to pollute training data and pose an automated poisoning attack on machine learning-based malware detection systems (e.g., DREBIN, DROIDAPIMINER, STORMDROID, and MAMADROID), and eventually mislead the detection tools. We further examine how machine learning classifiers can be mislead under four different attack models and significantly reduce detection accuracy. Apart from Android malware, to better protect mobile devices, we also discuss a general threat model of Android devices to investigate the capabilities of different attackers.
Article Search

proc time: 0.12