Abstract-Authentication of smartphone users is important because a lot of sensitive data is stored in the smartphone and the smartphone is also used to access various cloud data and services. However, smartphones are easily stolen or co-opted by an attacker. Beyond the initial login, it is highly desirable to re-authenticate end-users who are continuing to access securitycritical services and data. Hence, this paper proposes a novel authentication system for implicit, continuous authentication of the smartphone user based on behavioral characteristics, by leveraging the sensors already ubiquitously built into smartphones. We propose novel context-based authentication models to differentiate the legitimate smartphone owner versus other users. We systematically show how to achieve high authentication accuracy with different design alternatives in sensor and feature selection, machine learning techniques, context detection and multiple devices. Our system can achieve excellent authentication performance with 98.1% accuracy with negligible system overhead and less than 2.4% battery consumption.

No abstract

Smartphones are now frequently used by end-users as the portals to cloud-based services, and smartphones are easily stolen or co-opted by an attacker. Beyond the initial login mechanism, it is highly desirable to re-authenticate endusers who are continuing to access security-critical services and data, whether in the cloud or in the smartphone. But attackers who have gained access to a logged-in smartphone have no incentive to re-authenticate, so this must be done in an automatic, non-bypassable way. Hence, this paper proposes a novel authentication system, iAuth, for implicit, continuous authentication of the end-user based on his or her behavioral characteristics, by leveraging the sensors already ubiquitously built into smartphones. We design a system that gives accurate authentication using machine learning and sensor data from multiple mobile devices. Our system can achieve 92.1% authentication accuracy with negligible system overhead and less than 2% battery consumption.

Internet of things (IoT) applications have become increasingly popular in recent years, with applications ranging from building energy monitoring to personal health tracking and activity recognition. In order to leverage these data, automatic knowledge extraction -whereby we map from observations to interpretable states and transitions -must be done at scale. As such, we have seen many recent IoT data sets include annotations with a human expert specifying states, recorded as a set of boundaries and associated labels in a data sequence.ese data can be used to build automatic labeling algorithms that produce labels as an expert would. Here, we refer to human-specified boundaries as breakpoints. Traditional changepoint detection methods only look for statistically-detectable boundaries that are defined as abrupt variations in the generative parameters of a data sequence. However, we observe that breakpoints occur on more subtle boundaries that are non-trivial to detect with these statistical methods. In this work, we propose a new unsupervised approach, based on deep learning, that outperforms existing techniques and learns the more subtle, breakpoint boundaries with a high accuracy. rough extensive experiments on various real-world data sets -including human-activity sensing data, speech signals, and electroencephalogram (EEG) activity traces -we demonstrate the effectiveness of our algorithm for practical applications. Furthermore, we show that our approach achieves significantly be er performance than previous methods.

Federated learning is a recent approach for distributed model training without sharing the raw data of clients. It allows model training using the large amount of user data collected by edge and mobile devices, while preserving data privacy. A challenge in federated learning is that the devices usually have much lower computational power and communication bandwidth than machines in data centers. Training large-sized deep neural networks in such a federated setting can consume a large amount of time and resources. To overcome this challenge, we propose a method that integrates model pruning with federated learning in this paper, which includes initial model pruning at the server, further model pruning as part of the federated learning process, followed by the regular federated learning procedure. Our proposed approach can save the computation, communication, and storage costs compared to standard federated learning approaches. Extensive experiments on real edge devices validate the benefit of our proposed method.

An approach based on staggered multistep elution solid-phase extraction (SPE) capillary electrophoresis/tandem mass spectrometry (CE/MS/MS) was developed in the analysis of digested protein mixtures. On-line coupling of SPE with CE/MS was achieved using a two-leveled two-cross polydimethylsiloxane (PDMS)-based interface. Multistep elution SPE was used prior to CE to provide an additional dimension of separation, thus extending the separation capacity for the peptide mixture analysis. By decreasing in the number of co-eluting peptides, problems stemming from ionization suppression and finite MS/MS duty cycle were reduced. As a result, sequence coverage increased significantly using multistep elution SPE-CE/MS/MS compared to one-step elution SPE-CE/MS/MS in the analysis of a single protein tryptic digest (49% vs. 18%) and a six protein tryptic digest (22-71% vs. 10-44%). A staggered CE method was incorporated to increase the throughput. The electropherograms of consecutive CE runs were partially overlapped by injecting the sample plug at a fixed time interval. With the use of a 5 min injection interval, slightly poor results were obtained in comparison with the sequential CE method while the total analysis time was reduced to 28%.

A two-leveled, two cross PDMS-based interface for on-line coupling of SPE with CE-MS was proposed. In this interface, the SPE column and the CE separation column were positioned orthogonally and two crosses were fabricated on the interface. With the two cross design, the operation of SPE could be performed independently without unexpected flow through leakage into the separation column. The performance of the interface was optimized using a peptide mixture. The position of the SPE column related to the CE separation channel was found to be critical to the performance of the system. Under the optimal position, the separation efficiency was similar to a CE-MS experiment without SPE. The peptide signals were enhanced 50- to 100-fold and the repeatability was within 4% RSD for migration time and 10% RSD for peak area. A tryptic digest of cytochrome c was used to demonstrate the feasibility of the interface in protein identification at a level of 1 ng/microL.

No abstract