--Classification algorithms have been widely adopted to detect anomalies for various systems, e.g., IoT, cloud and face recognition, under the common assumption that the data source is clean, i.e., features and labels are correctly set. However, data collected from the wild can be unreliable due to careless annotations or malicious data transformation for incorrect anomaly detection. In this paper, we present a two-layer online learning framework for robust anomaly detection (RAD) in the presence of unreliable anomaly labels, where the first layer is to filter out the suspicious data, and the second layer detects the anomaly patterns from the remaining data. T o adapt to the online nature of anomaly detection, we extend RAD with additional features of repetitively cleaning, conflicting opinions of classifiers, and oracle knowledge. We online learn from the incoming data streams and continuously cleanse the data, so as to adapt to the increasing learning capacity from the larger accumulated data set. Moreover, we explore the concept of oracle learning that provides additional information of true labels for difficult data points. We specifically focus on three use cases, (i) detecting 10 classes of IoT attacks, (ii) predicting 4 classes of task failures of big data jobs, (iii) recognising 20 celebrities faces. Our evaluation results show that RAD can robustly improve the accuracy of anomaly detection, to reach up to 98% for IoT device attacks (i.e., 11%), up to 84% for cloud task failures (i.e., 20%) under 40% noise, and up to 74% for face recognition (i.e., 28%) under 30% noisy labels. The proposed RAD is general and can be applied to different anomaly detection algorithms. Anomaly detection is one of the core operations for enforcing dependability and performance in modern distributed systems [29], [44]. Anomalies can take various forms including erroneous data produced by a corrupted IoT device or the failure of a job executed in a datacenter [6], [7], [47]. Dealing with this issue has often been done in recent art by relying on machine learning-based classification algorithms over system logs [11], [13] or backend collected data [17], [46]. This work has been partly supported by the IRS (Initialtive de Recherche Strat egique) program DA TE. This work has been partly funded by the Swiss National Science Foundation NRP75 project 407540 167266 and TU Delft technology fellowship. As workloads at real systems are highly dynamic over time, it is even more challenging to predict anomalies that can not be easily distinguished from the system dynamics, compared to the systems with static workloads. In this context, a rising concern when applying classification algorithms is the accessibility to a reliable ground truth for anomalies [9].

Quantum computing exploits basic quantum phenomena such as state superposition and entanglement to perform computations. The Quantum Approximate Optimization Algorithm (QAOA) is arguably one of the leading quantum algorithms that can outperform classical state-of-the-art methods in the near term. QAOA is a hybrid quantum-classical algorithm that combines a parameterized quantum state evolution with a classical optimization routine to approximately solve combinatorial problems. The quality of the solution obtained by QAOA within a fixed budget of calls to the quantum computer depends on the performance of the classical optimization routine used to optimize the variational parameters. In this work, we propose an approach based on reinforcement learning (RL) to train a policy network that can be used to quickly find high-quality variational parameters for unseen combinatorial problem instances. The RL agent is trained on small problem instances which can be simulated on a classical computer, yet the learned RL policy is generalizable and can be used to efficiently solve larger instances. Extensive simulations using the IBM Qiskit Aer quantum circuit simulator demonstrate that our trained RL policy can reduce the optimality gap by a factor up to 8.61 compared with other off-the-shelf optimizers tested.

Deep neural networks (DNNs) are vulnerable to subtle adversarial perturbations applied to the input. These adversarial perturbations, though imperceptible, can easily mislead the DNN. In this work, we take a control theoretic approach to the problem of robustness in DNNs. We treat each individual layer of the DNN as a nonlinear dynamical system and use Lyapunov theory to prove stability and robustness locally. We then proceed to prove stability and robustness globally for the entire DNN. We develop empirically tight bounds on the response of the output layer, or any hidden layer, to adversarial perturbations added to the input, or the input of hidden layers. Recent works have proposed spectral norm regularization as a solution for improving robustness against l2 adversarial attacks. Our results give new insights into how spectral norm regularization can mitigate the adversarial effects. Finally, we evaluate the power of our approach on a variety of data sets and network architectures and against some of the well-known adversarial attacks.

Maximising the detection of intrusions is a fundamental and often critical aim of perimeter surveillance. Commonly, this requires a decision-maker to optimally allocate multiple searchers to segments of the perimeter. We consider a scenario where the decision-maker may sequentially update the searchers' allocation, learning from the observed data to improve decisions over time. In this work we propose a formal model and solution methods for this sequential perimeter surveillance problem. Our model is a combinatorial multi-armed bandit (CMAB) with Poisson rewards and a novel filtered feedback mechanism - arising from the failure to detect certain intrusions. Our solution method is an upper confidence bound approach and we derive upper and lower bounds on its expected performance. We prove that the gap between these bounds is of constant order, and demonstrate empirically that our approach is more reliable in simulated problems than competing algorithms.

Despite impressive performance on numerous visual tasks, Convolutional Neural Networks (CNNs) --- unlike brains --- are often highly sensitive to small perturbations of their input, e.g. adversarial noise leading to erroneous decisions. We propose to regularize CNNs using large-scale neuroscience data to learn more robust neural features in terms of representational similarity. We presented natural images to mice and measured the responses of thousands of neurons from cortical visual areas. Next, we denoised the notoriously variable neural activity using strong predictive models trained on this large corpus of responses from the mouse visual system, and calculated the representational similarity for millions of pairs of images from the model's predictions. We then used the neural representation similarity to regularize CNNs trained on image classification by penalizing intermediate representations that deviated from neural ones. This preserved performance of baseline models when classifying images under standard benchmarks, while maintaining substantially higher performance compared to baseline or control models when classifying noisy images. Moreover, the models regularized with cortical representations also improved model robustness in terms of adversarial attacks. This demonstrates that regularizing with neural data can be an effective tool to create an inductive bias towards more robust inference.

We investigate a framework for machine reading, inspired by real world information-seeking problems, where a meta question answering system interacts with a black box environment. The environment encapsulates a competitive machine reader based on BERT, providing candidate answers to questions, and possibly some context. To validate the realism of our formulation, we ask humans to play the role of a meta-answerer. With just a small snippet of text around an answer, humans can outperform the machine reader, improving recall. Similarly, a simple machine meta-answerer outperforms the environment, improving both precision and recall on the Natural Questions dataset. The system relies on joint training of answer scoring and the selection of conditioning information.

Eight artificial intelligence (AI) use-cases from six entities in Qatar were showcased during the Digital Transformation Workshop organised by the Qatar Digital Government Training Programme (QDGTP) in partnership with Microsoft. The event, an initiative by the Ministry of Transport and Communications (MoTC), was held on the sidelines of the recently concluded Qitcom 2019 at the Qatar National Convention Centre (QNCC) in Doha. The six entities included General Authority of Customs (GAC), Hamad Medical Corporation (HMC), Al Jazeera, the Ministry of Commerce and Industry (MoCI), Aspetar, and Aspire. Ali el-Sheshtawi from GAC presented a machine learning module developed by the authority to help in document processing by reducing risk of human error and time taken in handling documents, while HMC, represented by Ramez Raafat and Babu Ramesamy, presented the chatbot and auto coding use-cases respectively. Through the chatbot use-case, intelligent agent within the organisation will help shorten the path and time to get the needed information and understand the correct actions needed.

Eight artificial intelligence (AI) use-cases from six entities in Qatar were showcased during the Digital Transformation Workshop organised by the Qatar Digital Government Training Programme (QDGTP) in partnership with Microsoft. The event, an initiative by the Ministry of Transport and Communications (MoTC), was held on the sidelines of the recently concluded Qitcom 2019 at the Qatar National Convention Centre (QNCC) in Doha. The six entities included General Authority of Customs (GAC), Hamad Medical Corporation (HMC), Al Jazeera, the Ministry of Commerce and Industry (MoCI), Aspetar, and Aspire. Ali el-Sheshtawi from GAC presented a machine learning module developed by the authority to help in document processing by reducing risk of human error and time taken in handling documents, while HMC, represented by Ramez Raafat and Babu Ramesamy, presented the chatbot and auto coding use-cases respectively. Through the chatbot use-case, intelligent agent within the organisation will help shorten the path and time to get the needed information and understand the correct actions needed.

The US government funding in artificial intelligence has fallen short and the country needs to invest in research, train an AI-ready workforce and apply the technology to national security missions, a government-commissioned panel led by Google's former CEO said in an interim report on Monday. The National Security Commission on Artificial Intelligence (NSCAI), created by Congress last year, raised concerns about the progress China has made in this area. It also said the US government still faces enormous work before it can transition AI from "a promising technological novelty into a mature technology integrated into core national security missions." The commission thinks an allied effort on AI in the realm of national security is important, Robert Work, vice chairman of the NSCAI and a former deputy secretary of defense, told reporters. The NSCAI has spoken with Japan, Canada, the United Kingdom, Australia and the European Union, Work said. The challenge US officials face is that American industry and academic leaders have said that any such restrictions would harm the US economy.

Last December, China's top AI scientists gathered in Suzhou for the annual Wu Wenjun AI Science and Technology Award ceremony. They had every reason to expect a feel-good appreciation of China's accomplishments in AI. Yet the mood was decidedly downbeat. "After talking about our advantages, everyone mainly wants to talk about the shortcomings of Chinese AI capabilities in the near-term--where are China's AI weaknesses," said Li Deyi, the president of the Chinese Association for Artificial Intelligence. More than two years after the release of the New Generation Artificial Intelligence Development Plan (AIDP), China's top AI experts worry that Beijing's AI push will not live up to the hype.