Given that disturbances to the stable and normal operation of power systems have grown phenomenally, particularly in terms of unauthorized access to confidential and critical data, injection of malicious software, and exploitation of security vulnerabilities in a poorly patched software among others; then developing, as a countermeasure, an assessment solutions with machine learning capabilities to match up in real-time, with the growth and fast pace of these cyber-attacks, is not only critical to the security, reliability and safe operation of power system, but also germane to guaranteeing advanced monitoring and efficient threat detection. Using the Mississippi State University and Oak Ridge National Laboratory dataset, the study used an XGB Classifier modeling approach in machine learning to diagnose and assess power system disturbances, in terms of Attack Events, Natural Events and No-Events. As test results show, the model, in all the three sub-datasets, generally demonstrates good performance on all metrics, as it relates to accurately identifying and classifying all the three power system events.

The use of big data and algorithms to automate decision-making has been on the rise for many years. Data collection and "commercial surveillance" is a pervasive practice among social media companies and may other providers of online services. Join us as we consider the Federal Trade Commission's proposed rulemaking considering these issues as well as the "Blueprint for an AI Bill of Rights – Making Automated Systems Work for the American People" recently released by the White House Office of Science and Technology. CLE credit: CLE credit in CA, FL, IL, NJ (via reciprocity), NY, PA, TX, and VA is currently pending approval.

The symposium will explore how the application of A.I. in theatre and performance and ludic technologies can instantiate ruptures and disruptions to our contemporary cultural context and the everyday. It will also look at ways in which A.I. can be used in staging provocations and provocative design. This was a PETRAS event, chaired by Alan Chamberlain (University of Nottingham) & Dave De Roure (University of Oxford), the PI and CO-I of the EXIoT Project (PETRAS). It brings together the PETRAS, TAS Hub and nTAIL (AHRC) communities. The event is promoted as part of N-STAR, Nottingham Science, Technology, Art Research - in the Faculty of Science UoN, directed by Alan.

Expressing empathy is important in everyday conversations, and exploring how empathy arises is crucial in automatic response generation. Most previous approaches consider only a single factor that affects empathy. However, in practice, empathy generation and expression is a very complex and dynamic psychological process. A listener needs to find out events which cause a speaker's emotions (emotion cause extraction), project the events into some experience (knowledge extension), and express empathy in the most appropriate way (communication mechanism). To this end, we propose a novel approach, which integrates the three components - emotion cause, knowledge graph, and communication mechanism for empathetic response generation. Experimental results on the benchmark dataset demonstrate the effectiveness of our method and show that incorporating the key components generates more informative and empathetic responses.

Elon Musk's neuroscience startup Neuralink Corp. is expected to give a progress report on its brain-implant technology in a highly anticipated streamed event Wednesday night. In a tweet last week, the company teased a demo for the event, which begins at 9 p.m. New York time, with a short video that slowly spelled out the message "please join us for a show and tell." Some outside researchers said the video may indicate that a Neuralink device has been used to decode brain signals to type words on a screen, although they speculated that it would most likely be through a monkey or a wearable device. Neuralink has been testing its implant technology on nonhuman primates for several years, including in April 2021, when the company released a video showing that a monkey implanted with two Neuralink devices could play a videogame called Pong as the device translated its brain activity into commands with the help of machine-learning software. Other researchers have managed to use a brain-computer interface to enable monkeys to produce words on a computer screen.

The common practice for training commonsense models has gone from-human-to-corpus-to-machine: humans author commonsense knowledge graphs in order to train commonsense models. In this work, we investigate an alternative, from-machine-to-corpus-to-machine: general language models author these commonsense knowledge graphs to train commonsense models. Our study leads to a new framework, Symbolic Knowledge Distillation. As with prior art in Knowledge Distillation (Hinton et al., 2015), our approach uses larger models to teach smaller models. A key difference is that we distill knowledge symbolically-as text-in addition to the neural model. We also distill only one aspect-the commonsense of a general language model teacher, allowing the student to be a different type, a commonsense model. Altogether, we show that careful prompt engineering and a separately trained critic model allow us to selectively distill high-quality causal commonsense from GPT-3, a general language model. Empirical results demonstrate that, for the first time, a human-authored commonsense knowledge graph is surpassed by our automatically distilled variant in all three criteria: quantity, quality, and diversity. In addition, it results in a neural commonsense model that surpasses the teacher model's commonsense capabilities despite its 100x smaller size. We apply this to the ATOMIC resource, and share our new symbolic knowledge graph and commonsense models.

NYU Tandon Researchers analyzed the code generated by Github's Copilot, a program that leverages AI to write code. They found that for certain security-critical tasks the code contains security flaws 40 percent of the time. A pointer to the Wired article may be found here along with additional comments by Assistant Professor of Computer Science Brendan Dolan-Gavitt and Postdoctoral researcher Hammond Pearce.

While being an effective framework of learning a shared model across multiple edge devices, federated learning (FL) is generally vulnerable to Byzantine attacks from adversarial edge devices. While existing works on FL mitigate such compromised devices by only aggregating a subset of the local models at the server side, they still cannot successfully ignore the outliers due to imprecise scoring rule. In this paper, we propose an effective Byzantine-robust FL framework, namely dummy contrastive aggregation, by defining a novel scoring function that sensitively discriminates whether the model has been poisoned or not. Key idea is to extract essential information from every local models along with the previous global model to define a distance measure in a manner similar to triplet loss. Numerical results validate the advantage of the proposed approach by showing improved performance as compared to the state-of-the-art Byzantine-resilient aggregation methods, e.g., Krum, Trimmed-mean, and Fang.