Virtual assistants such as Apple's Siri or Amazon's AMZN Alexa have become popular technological helpers. Ask a virtual assistant to find a restaurant or tell you today's weather, a soothing AI voice obligingly responds. So why not a virtual assistant to help the U.S. Navy find Russian and Chinese submarines? The Navy wants a virtual assistant -- like the ones found on consumer smartphones -- to help overloaded sonar operators manage multiple anti-submarine warfare (ASW) systems. In particular, active sonar on Navy cruisers and destroyers come with a variety of settings.

A PwC report revealed that AI could transform the GDP of the UK up to 10.3% higher in 2030. The UK has been progressing towards the development of an AI strategy to guide the journey of digital transformation. The United Kingdom is a leader in promoting artificial intelligence startups. Further recent press reports stated how the state is planning to implement autonomous robots for pothole repairing and is anticipating opening a National Robotarium in 2022. The continuous effort towards improving its National AI strategy has made it one of the pioneers in AI and digital transformation.

Human beings, who live by the day and make decisions instantly, have become increasingly dependent on algorithms during the pandemic as machines turn all their inclinations into predictions. Artist Refik Anadol has brought a different artistic interpretation to this addiction with his "Machine Memories: Space" art exhibition, which has recently opened in the Turkish metropolis of Istanbul. Anadol's solo exhibition has also attracted the great attention of giant technology companies around the world. The manager of the Massachusetts Institute of Technology (MIT) Media Lab, which I visited many years ago at the invitation of Turkey's leading information and communication technologies company Türk Telekom, described the success criteria as "making an impact." Now I have met Anadol, an artist who has created an impact all over the world and is admired by data companies.

Earlier this month, a high-level, congressionally mandated commission released its long-awaited recommendations for how the United States should approach artificial intelligence (AI) for national security. The recommendations were part of a nearly 800-page report from the National Security Commission on AI (NSCAI) that advocated for the use of AI but also highlighted important conclusions on key risks posed by AI-enabled and autonomous weapons, particularly the dangers of unintended escalation of conflict. The commission identified these risks as stemming from several factors, including system failures, unknown interactions between these systems in armed conflict, challenges in human-machine interaction, as well as an increasing speed of warfare that reduces the time and space for de-escalation. These same factors also contribute to the inherent unpredictability in autonomous weapons, whether AI-enabled or not. From a humanitarian and legal perspective, the NSCAI could have explored in more depth the risks such unpredictability poses to civilians in conflict zones and to international law.

As financial institutions push out more digital products focused on speed and convenience, it creates additional points of vulnerability that fraudsters could exploit online. As a result, financial institutions are also expected to stay agile and deploy the latest technologies to protect their customers. In fact, the Movement Control Order (MCO) period last year presented a case study of what could happen as more financial transactions move online. Globally, a record-high number of scam and phishing sites were detected in 2020, according to Atlas VPN. "Propelled by the pandemic, there has been a significant shift towards digital transactions and real-time payments. This new normal has brought [not only] unprecedented efficiency and convenience but also an increase in payment-related fraud," says Abrar A Anwar, managing director and CEO of Standard Chartered Malaysia.

The latest top reads in banking, fintech, payments, cybersecurity, AI, IoT and risk management In this weeks selection; Interesting to know Digital Payments - US still in the Dark Ages Decentralized Finance - What it is and what it means Non-Fungible Tokens - Asset or Scam? Google Faces New Class Action Lawsuit for Privacy ViolationsBanks & Credit Unions Bank of America sees DeFi as potentially more disruptive than bitcoin. The bank breaks down why DeFi is fundamental How Digital Banking Can Help Credit Unions Succeed In 2021 Mobile banking in GCC surges due to Covid-19 Fintech Fintech companies must balance the pursuit of profit against ethical data usage Facebook Finally Explains Its Mysterious Wrist WearablePayments 7 Steps For Mobile Banking App Development UX Case Study: How to Create a Mobile Banking Super App The disruptive trends & companies transforming digital banking services in 2021 Cybersecurity Cybersecurity, skills concerns hamper Singapore SMB digitalisation efforts What exactly does Truecaller do with your data? A hacker's deep dive Building an Embedded Finance strategy: dos and don'ts 3 tips for mitigating cloud-related cybersecurity risks Why America will never be safe from cyberattacksArtificial Intelligence The Spectacular Growth of Artificial Intelligence Today Top 100 Artificial Intelligence Companies in the World 5 Common Pain Points With Machine Learning And How To Solve Them Digital Payments - US still in the Dark Ages Decentralized Finance - What it is and what it means Non-Fungible Tokens - Asset or Scam? Bank of America sees DeFi as potentially more disruptive than bitcoin.

Leveraging AI to undertake investigations of suspicious activities could significantly increase security teams' abilities to protect their organizations from cyber-attacks, according to Andrew Tsonchev, director of technology, Darktrace, speaking during the Infosecurity Magazine Online Summit EMEA 2021. The development of an'AI analyst' differs from the normal role of threat detection played by this type of technology in cybersecurity. In essence, it looks to "replicate the sort of steps taken by a human analyst in a SOC in a course of an investigation." Part of the driver for Darktrace's work in this area has been the extra pressure placed on security teams as a result of the changing working patterns in the past year. This has led to the growing use of remote endpoints as well as technologies such as SaaS and collaboration tools, expanding the threat landscape.

UiPath, a New York robotics automation company, on Friday said it had filed with the Securities and Exchange Commission for an initial public offering. The move comes not long after UiPath raised fresh capital from investors at a valuation of $35 billion, making the company one of the most valuable privately held tech businesses in the U.S., CNBC reported. The company, which plans to list on the New York Stock Exchange under the ticker symbol PATH, aims to raise $1 billion in the IPO, the SEC Form S-1 says. It has not detailed the number of shares it plans to offer or the estimated price range. In the fiscal year ended Jan.

Linear discriminant analysis (LDA) based classifiers tend to falter in many practical settings where the training data size is smaller than, or comparable to, the number of features. As a remedy, different regularized LDA (RLDA) methods have been proposed. These methods may still perform poorly depending on the size and quality of the available training data. In particular, the test data deviation from the training data model, for example, due to noise contamination, can cause severe performance degradation. Moreover, these methods commit further to the Gaussian assumption (upon which LDA is established) to tune their regularization parameters, which may compromise accuracy when dealing with real data. To address these issues, we propose a doubly regularized LDA classifier that we denote as R2LDA. In the proposed R2LDA approach, the RLDA score function is converted into an inner product of two vectors. By substituting the expressions of the regularized estimators of these vectors, we obtain the R2LDA score function that involves two regularization parameters. To set the values of these parameters, we adopt three existing regularization techniques; the constrained perturbation regularization approach (COPRA), the bounded perturbation regularization (BPR) algorithm, and the generalized cross-validation (GCV) method. These methods are used to tune the regularization parameters based on linear estimation models, with the sample covariance matrix's square root being the linear operator. Results obtained from both synthetic and real data demonstrate the consistency and effectiveness of the proposed R2LDA approach, especially in scenarios involving test data contaminated with noise that is not observed during the training phase.

The right to be forgotten states that a data subject has the right to erase their data from an entity storing it. In the context of machine learning (ML), it requires the ML model provider to remove the data subject's data from the training set used to build the ML model, a process known as \textit{machine unlearning}. While straightforward and legitimate, retraining the ML model from scratch upon receiving unlearning requests incurs high computational overhead when the training set is large. To address this issue, a number of approximate algorithms have been proposed in the domain of image and text data, among which SISA is the state-of-the-art solution. It randomly partitions the training set into multiple shards and trains a constituent model for each shard. However, directly applying SISA to the graph data can severely damage the graph structural information, and thereby the resulting ML model utility. In this paper, we propose GraphEraser, a novel machine unlearning method tailored to graph data. Its contributions include two novel graph partition algorithms, and a learning-based aggregation method. We conduct extensive experiments on five real-world datasets to illustrate the unlearning efficiency and model utility of GraphEraser. We observe that GraphEraser achieves 2.06$\times$ (small dataset) to 35.94$\times$ (large dataset) unlearning time improvement compared to retraining from scratch. On the other hand, GraphEraser achieves up to $62.5\%$ higher F1 score than that of random partitioning. In addition, our proposed learning-based aggregation method achieves up to $112\%$ higher F1 score than that of the majority vote aggregation.