Survey: Leakage and Privacy at Inference Time.

Leakage of data from publicly available Machine Learning (ML) models is an area of growing significance since commercial and government applications of ML can draw on multiple sources of data, potentially including users' and clients' sensitive data. We provide a comprehensive survey of contemporary advances on several fronts, covering involuntary data leakage which is natural to ML models, potential malicious leakage which is caused by privacy attacks, and currently available defence mechanisms. We focus on inference-time leakage, as the most likely scenario for publicly available models. We first discuss what leakage is in the context of different data, tasks, and model architectures. We then propose a taxonomy across involuntary and malicious leakage, followed by description of currently available defences, assessment metrics, and applications. We conclude with outstanding challenges and open questions, outlining some promising directions for future research.

Real-Time Adaptive Traffic Signal Control in a Connected and Automated Vehicle Environment: Optimisation of Signal Planning with Reinforcement Learning under Vehicle Speed Guidance.

Adaptive traffic signal control (ATSC) is an effective method to reduce traffic congestion in modern urban areas. Many studies adopted various approaches to adjust traffic signal plans according to real-time traffic in response to demand fluctuations to improve urban network performance (e.g., minimise delay). Recently, learning-based methods such as reinforcement learning (RL) have achieved promising results in signal plan optimisation. However, adopting these self-learning techniques in future traffic environments in the presence of connected and automated vehicles (CAVs) remains largely an open challenge. This study develops a real-time RL-based adaptive traffic signal control that optimises a signal plan to minimise the total queue length while allowing the CAVs to adjust their speed based on a fixed timing strategy to decrease total stop delays. The highlight of this work is combining a speed guidance system with a reinforcement learning-based traffic signal control. Two different performance measures are implemented to minimise total queue length and total stop delays. Results indicate that the proposed method outperforms a fixed timing plan (with optimal speed advisory in a CAV environment) and traditional actuated control, in terms of average stop delay of vehicle and queue length, particularly under saturated and oversaturated conditions.

Rapid age-grading and species identification of natural mosquitoes for malaria surveillance.

The malaria parasite, which is transmitted by several Anopheles mosquito species, requires more time to reach its human-transmissible stage than the average lifespan of mosquito vectors. Monitoring the species-specific age structure of mosquito populations is critical to evaluating the impact of vector control interventions on malaria risk. We present a rapid, cost-effective surveillance method based on deep learning of mid-infrared spectra of mosquito cuticle that simultaneously identifies the species and age class of three main malaria vectors in natural populations. Using spectra from over 40, 000 ecologically and genetically diverse An. gambiae, An. arabiensis, and An. coluzzii females, we develop a deep transfer learning model that learns and predicts the age of new wild populations in Tanzania and Burkina Faso with minimal sampling effort. Additionally, the model is able to detect the impact of simulated control interventions on mosquito populations, measured as a shift in their age structures. In the future, we anticipate our method can be applied to other arthropod vector-borne diseases.

Hysteresis-based supervisory control with application to non-pharmaceutical containment of COVID-19.

The recent COVID-19 outbreak has motivated an extensive development of non-pharmaceutical intervention policies for epidemics containment. While a total lockdown is a viable solution, interesting policies are those allowing some degree of normal functioning of the society, as this allows a continued, albeit reduced, economic activity and lessens the many societal problems associated with a prolonged lockdown. Recent studies have provided evidence that fast periodic alternation of lockdown and normal-functioning days may effectively lead to a good trade-off between outbreak abatement and economic activity. Nevertheless, the correct number of normal days to allocate within each period in such a way to guarantee the desired trade-off is a highly uncertain quantity that cannot be fixed a priori and that must rather be adapted online from measured data. This adaptation task, in turn, is still a largely open problem, and it is the subject of this work. In particular, we study a class of solutions based on hysteresis logic. First, in a rather general setting, we provide general convergence and performance guarantees on the evolution of the decision variable. Then, in a more specific context relevant for epidemic control, we derive a set of results characterizing robustness with respect to uncertainty and giving insight about how a priori knowledge about the controlled process may be used for fine-tuning the control parameters. Finally, we validate the results through numerical simulations tailored on the COVID-19 outbreak.

Prediction of weaning from mechanical ventilation using Convolutional Neural Networks.

Weaning from mechanical ventilation covers the process of liberating the patient from mechanical support and removing the associated endotracheal tube. The management of weaning from mechanical ventilation comprises a significant proportion of the care of critically ill intubated patients in Intensive Care Units (ICUs). Both prolonged dependence on mechanical ventilation and premature extubation expose patients to an increased risk of complications and increased health care costs. This work aims to develop a decision support model using routinely-recorded patient information to predict extubation readiness. In order to do so, we have deployed Convolutional Neural Networks (CNN) to predict the most appropriate treatment action in the next hour for a given patient state, using historical ICU data extracted from MIMIC-III. The model achieved 86% accuracy and 0.94 area under the receiver operating characteristic curve (AUC-ROC). We also performed feature importance analysis for the CNN model and interpreted these features using the DeepLIFT method. The results of the feature importance assessment show that the CNN model makes predictions using clinically meaningful and appropriate features. Finally, we implemented counterfactual explanations for the CNN model. This can help clinicians understand what feature changes for a particular patient would lead to a desirable outcome, i.e. readiness to extubate.

Post-lockdown abatement of COVID-19 by fast periodic switching.

COVID-19 abatement strategies have risks and uncertainties which could lead to repeating waves of infection. We show-as proof of concept grounded on rigorous mathematical evidence-that periodic, high-frequency alternation of into, and out-of, lockdown effectively mitigates second-wave effects, while allowing continued, albeit reduced, economic activity. Periodicity confers (i) predictability, which is essential for economic sustainability, and (ii) robustness, since lockdown periods are not activated by uncertain measurements over short time scales. In turn-while not eliminating the virus-this fast switching policy is sustainable over time, and it mitigates the infection until a vaccine or treatment becomes available, while alleviating the social costs associated with long lockdowns. Typically, the policy might be in the form of 1-day of work followed by 6-days of lockdown every week (or perhaps 2 days working, 5 days off) and it can be modified at a slow-rate based on measurements filtered over longer time scales. Our results highlight the potential efficacy of high frequency switching interventions in post lockdown mitigation. All code is available on Github at https://github.com/V4p1d/FPSP_Covid19. A software tool has also been developed so that interested parties can explore the proof-of-concept system.

Kemeny-based testing for COVID-19.

Testing, tracking and tracing abilities have been identified as pivotal in helping countries to safely reopen activities after the first wave of the COVID-19 virus. Contact tracing apps give the unprecedented possibility to reconstruct graphs of daily contacts, so the question is: who should be tested? As human contact networks are known to exhibit community structure, in this paper we show that the Kemeny constant of a graph can be used to identify and analyze bridges between communities in a graph. Our 'Kemeny indicator' is the value of the Kemeny constant in the new graph that is obtained when a node is removed from the original graph. We show that testing individuals who are associated with large values of the Kemeny indicator can help in efficiently intercepting new virus outbreaks, when they are still in their early stage. Extensive simulations provide promising results in early identification and in blocking the possible 'super-spreaders' links that transmit disease between different communities.

Efficient human-machine control with asymmetric marginal reliability input devices.

Input devices such as motor-imagery brain-computer interfaces (BCIs) are often unreliable. In theory, channel coding can be used in the human-machine loop to robustly encapsulate intention through noisy input devices but standard feedforward error correction codes cannot be practically applied. We present a practical and general probabilistic user interface for binary input devices with very high noise levels. Our approach allows any level of robustness to be achieved, regardless of noise level, where reliable feedback such as a visual display is available. In particular, we show efficient zooming interfaces based on feedback channel codes for two-class binary problems with noise levels characteristic of modalities such as motor-imagery based BCI, with accuracy <75%. We outline general principles based on separating channel, line and source coding in human-machine loop design. We develop a novel selection mechanism which can achieve arbitrarily reliable selection with a noisy two-state button. We show automatic online adaptation to changing channel statistics, and operation without precise calibration of error rates. A range of visualisations are used to construct user interfaces which implicitly code for these channels in a way that it is transparent to users. We validate our approach with a set of Monte Carlo simulations, and empirical results from a human-in-the-loop experiment showing the approach operates effectively at 50-70% of the theoretical optimum across a range of channel conditions.

Transmission of natural scene images through a multimode fibre.

The optical transport of images through a multimode fibre remains an outstanding challenge with applications ranging from optical communications to neuro-imaging. State of the art approaches either involve measurement and control of the full complex field transmitted through the fibre or, more recently, training of artificial neural networks that however, are typically limited to image classes belong to the same class as the training data set. Here we implement a method that statistically reconstructs the inverse transformation matrix for the fibre. We demonstrate imaging at high frame rates, high resolutions and in full colour of natural scenes, thus demonstrating general-purpose imaging capability. Real-time imaging over long fibre lengths opens alternative routes to exploitation for example for secure communication systems, novel remote imaging devices, quantum state control processing and endoscopy.

Neural network identification of people hidden from view with a single-pixel, single-photon detector.

Light scattered from multiple surfaces can be used to retrieve information of hidden environments. However, full three-dimensional retrieval of an object hidden from view by a wall has only been achieved with scanning systems and requires intensive computational processing of the retrieved data. Here we use a non-scanning, single-photon single-pixel detector in combination with a deep convolutional artificial neural network: this allows us to locate the position and to also simultaneously provide the actual identity of a hidden person, chosen from a database of people (N = 3). Artificial neural networks applied to specific computational imaging problems can therefore enable novel imaging capabilities with hugely simplified hardware and processing times.

Deep learning for real-time single-pixel video.

Single-pixel cameras capture images without the requirement for a multi-pixel sensor, enabling the use of state-of-the-art detector technologies and providing a potentially low-cost solution for sensing beyond the visible spectrum. One limitation of single-pixel cameras is the inherent trade-off between image resolution and frame rate, with current compressive (compressed) sensing techniques being unable to support real-time video. In this work we demonstrate the application of deep learning with convolutional auto-encoder networks to recover real-time 128 × 128 pixel video at 30 frames-per-second from a single-pixel camera sampling at a compression ratio of 2%. In addition, by training the network on a large database of images we are able to optimise the first layer of the convolutional network, equivalent to optimising the basis used for scanning the image intensities. This work develops and implements a novel approach to solving the inverse problem for single-pixel cameras efficiently and represents a significant step towards real-time operation of computational imagers. By learning from examples in a particular context, our approach opens up the possibility of high resolution for task-specific adaptation, with importance for applications in gas sensing, 3D imaging and metrology.

Mobile Phones As Surveillance Tools: Implementing and Evaluating a Large-Scale Intersectoral Surveillance System for Rabies in Tanzania.

Katie Hampson and colleagues describe their experience of developing and deploying a large-scale rabies surveillance system based on mobile phones in southern Tanzania.

Nonlinear modeling of FES-supported standing-up in paraplegia for selection of feedback sensors.

This paper presents analysis of the standing-up manoeuvre in paraplegia considering the body supportive forces as a potential feedback source in functional electrical stimulation (FES)-assisted standing-up. The analysis investigates the significance of arm, feet, and seat reaction signals to the human body center-of-mass (COM) trajectory reconstruction. The standing-up behavior of eight paraplegic subjects was analyzed, measuring the motion kinematics and reaction forces to provide the data for modeling. Two nonlinear empirical modeling methods are implemented--Gaussian process (GP) priors and multilayer perceptron artificial neural networks (ANN)--and their performance in vertical and horizontal COM component reconstruction is compared. As the input, ten sensory configurations that incorporated different number of sensors were evaluated trading off the modeling performance for variables chosen and ease-of-use in everyday application. For the purpose of evaluation, the root-mean-square difference was calculated between the model output and the kinematics-based COM trajectory. Results show that the force feedback in COM assessment in FES assisted standing-up is comparable alternative to the kinematics measurement systems. It was demonstrated that the GP provided better modeling performance, at higher computational cost. Moreover, on the basis of averaged results, the use of a sensory system incorporating a six-dimensional handle force sensor and an instrumented foot insole is recommended. The configuration is practical for realization and with the GP model achieves an average accuracy of COM estimation 16+/-1.8 mm in horizontal and 39+/-3.7 mm in vertical direction. Some other configurations analyzed in the study exhibit better modeling accuracy, but are less practical for everyday usage.