When your boss calls and tells you to wire $100,000 to a supplier, be on your toes. It could be a fake call. As if "phishing" phony emails weren't enough, on the rise now are "deep fake" audios that can be cloned with near perfection to sound almost perfect, and are easy to create for hackers. "It's on the rise, and something to watch out for," says Vijay Balasubramaniyan, the CEO of Pindrop, a company that offers biometric authentication for enterprise. Balasubramaniyan demonstrated during a security conference how easy it is to take audio from the internet and use machine learning to create recorded phrases into sentences that the human probably never said.

As AI – notably, Machine Learning continues to expand, government departments will increasingly use this technology to deliver advanced services to the public. In their recent report Committee on Standards in Public Life concluded: "Our message to government is that the UK's regulatory and governance framework for AI in the public sector remains a work in progress and deficiencies are notable. "The work of the Office for AI, the Alan Turing Institute, the Centre for Data Ethics and Innovation (CDEI), and the Information Commissioner's Office (ICO) are all commendable. But on the issues of transparency and data bias, in particular, there is an urgent need for practical guidance and enforceable regulation." In addition: "This review found that the Nolan Principles are strong, relevant, and do not need reformulating for AI. The Committee heard that they are principles of good governance that have stood, and continue to stand, the test of time.

All you need to know about the Legal and Regulatory Implications of #ArtificialIntelligence! We publish substantive articles as well as news updates on worldwide developments in #AI regulation.

More than 1,000 students are vying for places at the world's first dedicated artificial intelligence university in Abu Dhabi. The Mohamed bin Zayed University of Artificial Intelligence will swing open its doors in August, with demand high from those eager to be part of the inaugural class of 2020. The graduate-level institute revealed the bumper number of applicants are currently being put through a stringent vetting process ahead of the landmark opening term. Masters and PhD courses will be held at the forward-thinking seat of learning, which has cast the net far and wide across the globe in search of top talent. World's first artificial intelligence university to open in Abu Dhabi Artificial intelligence isn't coming to the UAE - it is already here During the university's first advisory board meeting, Dr Sultan Al Jaber, Minister of State, said the first wave of students would be at the forefront of a new era of innovation in the country.

While deep learning in 3D domain has achieved revolutionary performance in many tasks, the robustness of these models has not been sufficiently studied or explored. Regarding the 3D adversarial samples, most existing works focus on manipulation of local points, which may fail to invoke the global geometry properties, like robustness under linear projection that preserves the Euclidean distance, i.e., isometry. In this work, we show that existing state-of-the-art deep 3D models are extremely vulnerable to isometry transformations. Armed with the Thompson Sampling, we develop a black-box attack with success rate over 95\% on ModelNet40 data set. Incorporating with the Restricted Isometry Property, we propose a novel framework of white-box attack on top of spectral norm based perturbation. In contrast to previous works, our adversarial samples are experimentally shown to be strongly transferable. Evaluated on a sequence of prevailing 3D models, our white-box attack achieves success rates from 98.88\% to 100\%. It maintains a successful attack rate over 95\% even within an imperceptible rotation range $[\pm 2.81^{\circ}]$.

Weak supervision is a popular method for building machine learning models without relying on ground truth annotations. Instead, it generates probabilistic training labels by estimating the accuracies of multiple noisy labeling sources (e.g., heuristics, crowd workers). Existing approaches use latent variable estimation to model the noisy sources, but these methods can be computationally expensive, scaling superlinearly in the data. In this work, we show that, for a class of latent variable models highly applicable to weak supervision, we can find a closed-form solution to model parameters, obviating the need for iterative solutions like stochastic gradient descent (SGD). We use this insight to build FlyingSquid, a weak supervision framework that runs orders of magnitude faster than previous weak supervision approaches and requires fewer assumptions. In particular, we prove bounds on generalization error without assuming that the latent variable model can exactly parameterize the underlying data distribution. Empirically, we validate FlyingSquid on benchmark weak supervision datasets and find that it achieves the same or higher quality compared to previous approaches without the need to tune an SGD procedure, recovers model parameters 170 times faster on average, and enables new video analysis and online learning applications.

Facial recognition software provider Clearview AI has revealed that its entire client list was stolen by someone who'gained unauthorized access' to company documents and data. According to a notice sent to its customers, Cleaview AI said that in addition to its client list, the intruder had gained access to the number of user accounts associated with each client, as well as the number of searches conducted through those accounts. The company didn't specify how the security breach had occurred nor who might have been responsible, and it claimed its servers and internal network hadn't been compromised. Facial recognition software company Clearview AI has revealed a security breach that exposed it's client list and number of searches those clients made'Unfortunately, data breaches are part of life in the 21st century,' Clearview attorney Tor Ekeland told The Daily Beast, who broke the story. 'Our servers were never accessed.

Although the opportunities to apply analytics in the public sector are abundant, cultural and technical challenges must be overcome before government agencies can claim to be fully developed, enterprise-wide, analytically competitive organizations. Building an analytical culture where data is widely used to evaluate hypotheses is crucial for an analytically competitive organization. Despite the successes that the public sector has seen in the past with analytics, data analysis is not integrated into most decision-making processes. This can partly be attributed to the enormous variety of tasks in many different fields that government organizations perform. In such varied environments, one-size-fits-all approach to cultural change is often ineffective, and customized approaches training, policies, and incentives are necessary.