Data poisoning--the process by which an attacker takes control of a model by making imperceptible changes to a subset of the training data--is an emerging threat in the context of neural networks. Existing attacks for data poisoning have relied on hand-crafted heuristics. Instead, we pose crafting poisons more generally as a bi-level optimization problem, where the inner level corresponds to training a network on a poisoned dataset and the outer level corresponds to updating those poisons to achieve a desired behavior on the trained model. We then propose MetaPoison, a first-order method to solve this optimization quickly. MetaPoison is effective: it outperforms previous clean-label poisoning methods by a large margin under the same setting. MetaPoison is robust: its poisons transfer to a variety of victims with unknown hyperparameters and architectures. MetaPoison is also general-purpose, working not only in fine-tuning scenarios, but also for end-to-end training from scratch with remarkable success, e.g. causing a target image to be misclassified 90% of the time via manipulating just 1% of the dataset. Additionally, MetaPoison can achieve arbitrary adversary goals not previously possible--like using poisons of one class to make a target image don the label of another arbitrarily chosen class. Finally, MetaPoison works in the real-world. We demonstrate successful data poisoning of models trained on Google Cloud AutoML Vision. Code and premade poisons are provided at https://github.com/wronnyhuang/metapoison

The N-Tuple Bandit Evolutionary Algorithm (NTBEA) has proven very effective in optimising algorithm parameters in Game AI. A potential weakness is the use of a simple average of all component Tuples in the model. This study investigates a refinement to the N-Tuple model used in NTBEA by weighting these component Tuples by their level of information and specificity of match. We introduce weighting functions to the model to obtain Weighted- NTBEA and test this on four benchmark functions and two game environments. These tests show that vanilla NTBEA is the most reliable and performant of the algorithms tested. Furthermore we show that given an iteration budget it is better to execute several independent NTBEA runs, and use part of the budget to find the best recommendation from these runs.

A large body of compelling evidence has been accumulated demonstrating that embodiment - the agent's physical setup, including its shape, materials, sensors and actuators - is constitutive for any form of cognition and as a consequence, models of cognition need to be embodied. In contrast to methods from empirical sciences to study cognition, robots can be freely manipulated and virtually all key variables of their embodiment and control programs can be systematically varied. As such, they provide an extremely powerful tool of investigation. We present a robotic bottom-up or developmental approach, focusing on three stages: (a) low-level behaviors like walking and reflexes, (b) learning regularities in sensorimotor spaces, and (c) human-like cognition. We also show that robotic based research is not only a productive path to deepening our understanding of cognition, but that robots can strongly benefit from human-like cognition in order to become more autonomous, robust, resilient, and safe.

Americans are increasingly being spotted wearing face masks in public amid the coronavirus pandemic, as are people are around the globe. Soon, the Centers for Disease Control and Prevention (CDC) may advise all Americans to cover their faces when they leave the house, the Washington Post reported. The agency is weighing that recommendation after initially telling Americans that they didn't need to wear masks and that anything other than a high-grade N95 medical mask would do little to prevent infection any way. Research on how well various types of masks and face coverings varies but, recently, and in light of the pandemic of COVID-19, experts are increasingly leaning toward the notion that something is better than nothing. A University of Oxford study published on March 30 concluded that surgical masks are just as effective at preventing respiratory infections as N95 masks for doctors, nurses and other health care workers.

Machine Learning and Artificial Intelligence are offering an entirely new level of possibilities to businesses worldwide, one of those possibilities is Fraud Detection. Financial institutions and banks will never be the same with the opportunities technology offers to deal with criminal activities and fight internet fraud. Learn how it works in this post! The things people used to buy at shops years ago are now purchased online, no matter what they are: furniture, food, or clothes. As a result, the global E-Commerce market is rapidly rising and estimated to reach $4.9 trillion by 2021. This undoubtedly triggers members of the criminal world to find paths to victims' wallets through the Web. Federal, local, and state law enforcement agencies along with private organizations reported 3 million cases of identity theft in 2019. Money was lost in about 25% of these cases.

How long can coronavirus remain infectious in the air and on contaminated surfaces? New study finds that the novel coronavirus, SARS-CoV-2, can remain viable on plastic and steel for several days, highlighting the importance of hand washing and surface cleaning amidst the current outbreak. However, the consortium is not the only group harnessing the power of artificial intelligence in the fight against the coronavirus pandemic. Other scientists are attempting to develop a computer model of the coronavirus, which they hope will aid in the development of new drugs and vaccines. Continuing on from the initial work conducted by the University of Texas at Austin (TX, USA), biochemists from the University of California, San Diego are endeavoring to build the first complete all-atom model of the SARS-COV-2 coronavirus envelope.

Sign in to report inappropriate content. Tech San Diego Presents the AI & Machine Learning Series with Claire Weston, CEO and Founder of Reveal Biosciences Sponsored by Cooley LLP AI's growing role in life sciences In the above webinar, Claire talks about how AI is revolutionizing pathology. Hear how Reveal Biosciences is on the cutting edge of leveraging AI to enhance research and improve global healthcare.

Abstract: Gaussian process regression is ubiquitous in spatial statistics, machine learning, and the surrogate modeling of computer simulation experiments. Fortunately their prowess as accurate predictors, along with an appropriate quantification of uncertainty, does not derive from difficult-to-understand methodology and cumbersome implementation. We will cover the basics, and provide a practical tool-set ready to be put to work in diverse applications. The presentation will involve accessible slides authored in Rmarkdown, with reproducible examples spanning bespoke implementation to add-on packages. Instructor Bio: Robert Gramacy is a Professor of Statistics in the College of Science at Virginia Polytechnic and State University (Virginia Tech).

AU10TIX, a global cloud-based, machine learning, ID verification, and authentication platform, recently joined the FIDO Alliance. The Global Machine Learning Market is expected to grow by USD 11.16 bn during 2020-2024, progressing at a CAGR of 39% during the forecast period

Neural networks can perform well on tasks such as image classification, language translation, and game playing. However, they usually fail to perform well in tasks that need human abstraction. Activities such as catching balls mid-air or juggling multiple balls, which the humans have mastered, need an intuitive understanding of dynamics of how physical bodies behave. We don't take time out to calculate the trajectories before hitting the ball. Machine learning models lack many basic intuitions about the dynamics of the physical world.