Voice user interfaces and digital assistants are rapidly entering our homes and becoming integrated with all our devices. These always-on services capture and transmit our audio data to powerful cloud services for further processing and subsequent actions. Our voices and raw audio signals collected through these devices contain a host of sensitive paralinguistic information that is transmitted to service providers regardless of deliberate or false triggers. As sensitive attributes like our identity, gender, indicators of mental health status, alongside moods, emotions and their temporal patterns, are easily inferred using deep acoustic models, we encounter a new generation of privacy risks by using these services. One approach to mitigate the risk of paralinguistic-based privacy breaches is to exploit a combination of cloud-based processing with privacy-preserving on-device paralinguistic information filtering prior to transmitting voice data. In this paper we introduce EDGY, a new lightweight disentangled representation learning model that transforms and filters high-dimensional voice data to remove sensitive attributes at the edge prior to offloading to the cloud. We evaluate EDGY's on-device performance, and explore optimization techniques, including model pruning and quantization, to enable private, accurate and efficient representation learning on resource-constrained devices. Our experimental results show that EDGY runs in tens of milliseconds with minimal performance penalties or accuracy losses in speech recognition using only a CPU and a single core ARM device without specialized hardware.
The proliferation of IoT sensors and edge devices makes it possible to use deep learning models to recognise daily activities locally using in-home monitoring technologies. Recently, federated learning systems that use edge devices as clients to collect and utilise IoT sensory data for human activity recognition have been commonly used as a new way to combine local (individual-level) and global (group-level) models. This approach provides better scalability and generalisability and also offers higher privacy compared with the traditional centralised analysis and learning models. The assumption behind federated learning, however, relies on supervised learning on clients. This requires a large volume of labelled data, which is difficult to collect in uncontrolled IoT environments such as remote in-home monitoring. In this paper, we propose an activity recognition system that uses semi-supervised federated learning, wherein clients conduct unsupervised learning on autoencoders with unlabelled local data to learn general representations, and a cloud server conducts supervised learning on an activity classifier with labelled data. Our experimental results show that using autoencoders and a long short-term memory (LSTM) classifier, the accuracy of our proposed system is comparable to that of a supervised federated learning system. Meanwhile, we demonstrate that our system is not affected by the Non-IID distribution of local data, and can even achieve better accuracy than supervised federated learning on some datasets. Additionally, we show that our proposed system can reduce the number of needed labels in the system and the size of local models without losing much accuracy, and has shorter local activity recognition time than supervised federated learning.
Training a deep neural network (DNN) via federated learning allows participants to share model updates (gradients), instead of the data itself. However, recent studies show that unintended latent information (e.g. gender or race) carried by the gradients can be discovered by attackers, compromising the promised privacy guarantee of federated learning. Existing privacy-preserving techniques (e.g. differential privacy) either have limited defensive capacity against the potential attacks, or suffer from considerable model utility loss. Moreover, characterizing the latent information carried by the gradients and the consequent privacy leakage has been a major theoretical and practical challenge. In this paper, we propose two new metrics to address these challenges: the empirical $\mathcal{V}$-information, a theoretically grounded notion of information which measures the amount of gradient information that is usable for an attacker, and the sensitivity analysis that utilizes the Jacobian matrix to measure the amount of changes in the gradients with respect to latent information which further quantifies private risk. We show that these metrics can localize the private information in each layer of a DNN and quantify the leakage depending on how sensitive the gradients are with respect to the latent information. As a practical application, we design LatenTZ: a federated learning framework that lets the most sensitive layers to run in the clients' Trusted Execution Environments (TEE). The implementation evaluation of LatenTZ shows that TEE-based approaches are promising for defending against powerful property inference attacks without a significant overhead in the clients' computing resources nor trading off the model's utility.
In this paper we show that the data plane of commodity programmable (Network Interface Cards) NICs can run neural network inference tasks required by packet monitoring applications, with low overhead. This is particularly important as the data transfer costs to the host system and dedicated machine learning accelerators, e.g., GPUs, can be more expensive than the processing task itself. We design and implement our system -- N3IC -- on two different NICs and we show that it can greatly benefit three different network monitoring use cases that require machine learning inference as first-class-primitive. N3IC can perform inference for millions of network flows per second, while forwarding traffic at 40Gb/s. Compared to an equivalent solution implemented on a general purpose CPU, N3IC can provide 100x lower processing latency, with 1.5x increase in throughput.
Current deep neural architectures for processing sensor data are mainly designed for data coming from a fixed set of sensors, with a fixed sampling rate. Changing the dimensions of the input data causes considerable accuracy loss, unnecessary computations, or application failures. To address this problem, we introduce a {\em dimension-adaptive pooling}~(DAP) layer that makes deep architectures robust to temporal changes in sampling rate and in sensor availability. DAP operates on convolutional filter maps of variable dimensions and produces an input of fixed dimensions suitable for feedforward and recurrent layers. Building on this architectural improvement, we propose a {\em dimension-adaptive training}~(DAT) procedure to generalize over the entire space of feasible data dimensions at the inference time. DAT comprises the random selection of dimensions during the forward passes and optimization with accumulated gradients of several backward passes. We then combine DAP and DAT to transform existing non-adaptive deep architectures into a {\em Dimension-Adaptive Neural Architecture}~(DANA) without altering other architectural aspects. Our solution does not need up-sampling or imputation, thus reduces unnecessary computations at inference time. Experimental results on public datasets show that DANA prevents losses in classification accuracy of the state-of-the-art deep architectures, under dynamic sensor availability and varying sampling rates.
We present DarkneTZ, a framework that uses an edge device's Trusted Execution Environment (TEE) in conjunction with model partitioning to limit the attack surface against Deep Neural Networks (DNNs). Increasingly, edge devices (smartphones and consumer IoT devices) are equipped with pre-trained DNNs for a variety of applications. This trend comes with privacy risks as models can leak information about their training data through effective membership inference attacks (MIAs). We evaluate the performance of DarkneTZ, including CPU execution time, memory usage, and accurate power consumption, using two small and six large image classification models. Due to the limited memory of the edge device's TEE, we partition model layers into more sensitive layers (to be executed inside the device TEE), and a set of layers to be executed in the untrusted part of the operating system. Our results show that even if a single layer is hidden, we can provide reliable model privacy and defend against state of the art MIAs, with only 3% performance overhead. When fully utilizing the TEE, DarkneTZ provides model protections with up to 10% overhead.
Machine Learning as a Service (MLaaS) operators provide model training and prediction on the cloud. MLaaS applications often rely on centralised collection and aggregation of user data, which could lead to significant privacy concerns when dealing with sensitive personal data. To address this problem, we propose PrivEdge, a technique for privacy-preserving MLaaS that safeguards the privacy of users who provide their data for training, as well as users who use the prediction service. With PrivEdge, each user independently uses their private data to locally train a one-class reconstructive adversarial network that succinctly represents their training data. As sending the model parameters to the service provider in the clear would reveal private information, PrivEdge secret-shares the parameters among two non-colluding MLaaS providers, to then provide cryptographically private prediction services through secure multi-party computation techniques. We quantify the benefits of PrivEdge and compare its performance with state-of-the-art centralised architectures on three privacy-sensitive image-based tasks: individual identification, writer identification, and handwritten letter recognition. Experimental results show that PrivEdge has high precision and recall in preserving privacy, as well as in distinguishing between private and non-private images. Moreover, we show the robustness of PrivEdge to image compression and biased training data. The source code is available at https://github.com/smartcameras/PrivEdge.
We are increasingly surrounded by applications, connected devices, services, and smart environments which require fine-grained access to various personal data. The inherent complexities of our personal and professional policies and preferences in interactions with these analytics services raise important challenges in privacy. Moreover, due to sensitivity of the data and regulatory and technical barriers, it is not always feasible to do these policy negotiations in a centralized manner. In this paper we present PoliBox, a decentralized, edge-based framework for policy-based personal data analytics. PoliBox brings together a number of existing established components to provide privacy-preserving analytics within a distributed setting. We evaluate our framework using a popular exemplar of private analytics, Federated Learning, and demonstrate that for varying model sizes and use cases, PoliBox is able to perform accurate model training and inference within very reasonable resource and time budgets.
Sensitive inferences and user re-identification are major threats to privacy when raw sensor data from wearable or portable devices are shared with cloud-assisted applications. To mitigate these threats, we propose mechanisms to transform sensor data before sharing them with applications running on users' devices. These transformations aim at eliminating patterns that can be used for user re-identification or for inferring potentially sensitive activities, while introducing a minor utility loss for the target application (or task). We show that, on gesture and activity recognition tasks, we can prevent inference of potentially sensitive activities while keeping the reduction in recognition accuracy of non-sensitive activities to less than 5 percentage points. We also show that we can reduce the accuracy of user re-identification and of the potential inference of gender to the level of a random guess, while keeping the accuracy of activity recognition comparable to that obtained on the original data.
Contextual bandit algorithms (CBAs) often rely on personal data to provide recommendations. This means that potentially sensitive data from past interactions are utilized to provide personalization to end-users. Using a local agent on the user's device protects the user's privacy, by keeping the data locally, however, the agent requires longer to produce useful recommendations, as it does not leverage feedback from other users. This paper proposes a technique we call Privacy-Preserving Bandits (P2B), a system that updates local agents by collecting feedback from other agents in a differentially-private manner. Comparisons of our proposed approach with a non-private, as well as a fully-private (local) system, show competitive performance on both synthetic benchmarks and real-world data. Specifically, we observed a decrease of 2.6% and 3.6% in multi-label classification accuracy, and a CTR increase of 0.0025 in online advertising for a privacy budget $\epsilon \approx$ 0.693. These results suggest P2B is an effective approach to problems arising in on-device privacy-preserving personalization.