Cloud vendors are increasingly offering machine learning services as part of their platform and services portfolios. These services enable the deployment of machine learning models on the cloud that are offered on a pay-per-query basis to application developers and end users. However recent work has shown that the hosted models are susceptible to extraction attacks. Adversaries may launch queries to steal the model and compromise future query payments or privacy of the training data. In this work, we present a cloudbased extraction monitor that can quantify the extraction status of models by observing the query and response streams of both individual and colluding adversarial users. We present a novel technique that uses information gain to measure the model learning rate by users with increasing number of queries. Additionally, we present an alternate technique that maintains intelligent query summaries to measure the learning rate relative to the coverage of the input feature space in the presence of collusion. Both these approaches have low computational overhead and can easily be offered as services to model owners to warn them of possible extraction attacks from adversaries. We present performance results for these approaches for decision tree models deployed on BigML MLaaS platform, using open source datasets and different adversarial attack strategies.

No abstract

Demand response (DR) programs encourage end-use customers to alter their power consumption in response to DR events such as change in real-time electricity prices. Facilitating household participation in DR programs is essential as the residential sector accounts for a sizable portion of the total energy consumed. However, manually tracking energy prices and deciding on how to schedule home appliances can be a challenge for residential consumers who are accustomed to fixed price electricity tariffs. In this work, we present Yupik, a system that helps users respond to realtime electricity prices while being sensitive to their context and lifestyle. Yupik combines sensing, analytics, and optimization to generate appliance usage schedules that may be used by households to minimize their energy bill as well as potential lifestyle disruptions. Yupik uses jPlugs, appliance level energy metering devices, to continuously monitor the power usage by various home appliances. The consumption patterns as well as data from external sources are analyzed using data mining algorithms to infer user's preferred usage profile. Using the preferred profile as a reference, Yupik's optimization engine generates multiple usage plans that attempt to minimize energy and inconvenience costs. Some of Yupik's capabilities are demonstrated with the help of preliminary data collected from a home that was instrumented with jPlugs to monitor the power usage of a few devices.

No abstract

No abstract

Managing the Quality-of-Experience (QoE) of video streaming for wireless clients is becoming increasingly important due to the rapid growth of video traffic on wireless networks. The inherent variability of the wireless channel as well as the Variable Bit Rate (VBR) of the compressed video streams make QoE management a challenging problem. Prior work has studied this problem in the context of transmitting a single video stream. In this paper, we investigate multiplexing schemes to transmit multiple video streams from a base station to mobile clients that use number of playout stalls as a performance metric.In this context, we present an epoch-by-epoch framework to fairly allocate wireless transmission slots to streaming videos. In each epoch our scheme essentially reduces the vulnerability to stalling by allocating slots to videos in a way that maximizes the minimum 'playout lead' across all videos. Next, we show that the problem of allocating slots fairly is NP-complete even for a constant number of videos. We then present a fast lead-aware greedy algorithm for the problem. Our choice of greedy algorithm is motivated by the fact that this algorithm is optimal when the channel quality of a user remains unchanged within an epoch (but different users may experience different channel quality). Moreover, our experimental results based on public MPEG-4 video traces and wireless channel traces that we collected from a WiMAX test-bed show that the lead-aware greedy approach performs a fair distribution of stalls across the clients when compared to other algorithms, while still maintaining similar or lower average number of stalls per client.

No abstract

No abstract