Reinforcement Learning (RL) has quickly achieved impressive results in a wide variety of control problems, from video games to more real-world applications like autonomous driving and cyberdefense [Vinyals et al., 2019, Galias et al., 2019, Nguyen and Reddi, 2019]. However, as RL becomes integrated into more high risk application areas, security vulnerabilities become more pressing. One such security risk is data poisoning, wherein an attacker maliciously modifies training data to achieve certain adversarial goals. In this work, we carry out a novel data poisoning attack for RL agents, which involves imperceptibly altering a small amount of training data. The effect is the trained agent performs its task normally until it encounters a particular state chosen by the attacker, where it misbehaves catastrophically. Although the complex mechanics of RL have historically made data poisoning for RL challenging, we successfully apply gradient alignment, an approach from supervised learning, to RL [Geiping et al., 2020]. Specifically, we attack RL agents playing Atari games, and demonstrate that we can produce agents that effectively play the game, until shown a particular cue. We demonstrate that effective cues include a specific target state of the attacker's choosing, or, more subtly, a translucent watermark appearing on a portion of any state.

Fifth generation (5G) networks and beyond envisions massive Internet of Things (IoT) rollout to support disruptive applications such as extended reality (XR), augmented/virtual reality (AR/VR), industrial automation, autonomous driving, and smart everything which brings together massive and diverse IoT devices occupying the radio frequency (RF) spectrum. Along with spectrum crunch and throughput challenges, such a massive scale of wireless devices exposes unprecedented threat surfaces. RF fingerprinting is heralded as a candidate technology that can be combined with cryptographic and zero-trust security measures to ensure data privacy, confidentiality, and integrity in wireless networks. Motivated by the relevance of this subject in the future communication networks, in this work, we present a comprehensive survey of RF fingerprinting approaches ranging from a traditional view to the most recent deep learning (DL) based algorithms. Existing surveys have mostly focused on a constrained presentation of the wireless fingerprinting approaches, however, many aspects remain untold. In this work, however, we mitigate this by addressing every aspect - background on signal intelligence (SIGINT), applications, relevant DL algorithms, systematic literature review of RF fingerprinting techniques spanning the past two decades, discussion on datasets, and potential research avenues - necessary to elucidate this topic to the reader in an encyclopedic manner.

Graph kernels are historically the most widely-used technique for graph classification tasks. However, these methods suffer from limited performance because of the hand-crafted combinatorial features of graphs. In recent years, graph neural networks (GNNs) have become the state-of-the-art method in downstream graph-related tasks due to their superior performance. Most GNNs are based on Message Passing Neural Network (MPNN) frameworks. However, recent studies show that MPNNs can not exceed the power of the Weisfeiler-Lehman (WL) algorithm in graph isomorphism test. To address the limitations of existing graph kernel and GNN methods, in this paper, we propose a novel GNN framework, termed \textit{Kernel Graph Neural Networks} (KerGNNs), which integrates graph kernels into the message passing process of GNNs. Inspired by convolution filters in convolutional neural networks (CNNs), KerGNNs adopt trainable hidden graphs as graph filters which are combined with subgraphs to update node embeddings using graph kernels. In addition, we show that MPNNs can be viewed as special cases of KerGNNs. We apply KerGNNs to multiple graph-related tasks and use cross-validation to make fair comparisons with benchmarks. We show that our method achieves competitive performance compared with existing state-of-the-art methods, demonstrating the potential to increase the representation ability of GNNs. We also show that the trained graph filters in KerGNNs can reveal the local graph structures of the dataset, which significantly improves the model interpretability compared with conventional GNN models.

As the capabilities of Artificial Intelligence systems increase everyday, government officials are under more pressure than ever to develop a comprehensive and robust set of policies and laws that holds these algorithms accountable for their decisions. The question on whether these algorithms should be held accountable has gained attention over the past few years through scandals such as Google's mislabeling of images and Microsoft Tay's racist tweets. In determining whether an algorithm should be held accountable or not, it is important to break the topic down into key questions. The first is what task is the algorithm completing? What are the implications to individuals/society resulting from the algorithm's decision.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. BAGHDAD -- Chanting anti-American slogans, hundreds of people rallied in the Iraqi capital Saturday to mark the anniversary of the killing of a powerful Iranian general and a top Iraqi militia leader in a U.S. drone strike. The crowd called for the expulsion of remaining American forces from Iraq during the demonstration commemorating the airstrike at Baghdad airport. The strike killed Gen. Qassim Soleimani, who was the head of Iran's elite Quds Force, and Abu Mahdi al-Muhandis, deputy commander of Iran-backed militias in Iraq known as the Popular Mobilization Forces.

Predicting future events is hard, but it's among the most important tasks a journalist can perform. Especially if you work at a section called Future Perfect. Our mission is to explain the world around us to our readers, and it's impossible to do that without anticipating what comes next. Will inflation continue to rise in the US and Europe, or level off? Will the Supreme Court allow states to ban abortion, eliminating legal access in red states? Will Brazil's 212 million people be led by a left-wing populist, or a far-right anti-vaxxer? All of these questions matter, and preparing ourselves for potential outcomes -- and having a good sense of how likely specific outcomes are -- is a major part of explaining the world accurately. And if policymakers could rely on accurate predictions about the outcome of a foreign war or the advisability of a budget proposal, they could make much better policy decisions. Being good at predictions is a skill like any other -- you have to practice it.

New Delhi: The Indian Army with the help of National Security Council Secretariat (NSCS) has established a Quantum and Artificial Intelligence (AI) Lab at Military College of Telecommunication Engineering in Madhya Pradesh's Mhow to spearhead research and training in this key developing field. Key thrust areas are Quantum Key Distribution, Quantum Communication, Quantum Computing and Post Quantum Cryptography, the force said. Indian Army chief General M.M. Naravane visited the facility to take stock of the situation and see technological research being taken by the labs. Indian Army has established an Artificial Intelligence (AI) Centre at the same institution with over 140 deployments in forward areas and active support of the industry and academia.

Testing the best: There's only one way to figure that out: ask some users. So that's what researchers from Harvard and Google Brain did, in a series of studies. Test subjects looked at different combinations of inputs, outputs, and explanations around a machine learning algorithm that was designed to learn the dietary habits or medical conditions of an alien (Yes, seriously--alien life was chosen to avoid the test subject's own biases creeping in). Users then scored the different combinations. Keep it short: Longer explanations were found to be more difficult to parse than shorter ones--though breaking up the same amount of text into many short lines was somehow better than making people read a few longer lines.

Niels Bohr, the Nobel laureate in Physics and father of the atomic model, is quoted as saying, "Prediction is very difficult, especially if it's about the future!" I picked Ron Toews, not to criticize, but to use his AI predictions for 2021 (made last year) as an example of how harrowing this game can be. I'll admit, I'm too timid to make predictions, but I do enjoy tracking how well others did in the previous year. Also, Toews is very well informed about the subject matter, and he's not a vendor, whose "predictions" are not always objective. Here's my quick hits on Toews' ten AI predictions for 2021 - and how they fared.

AI regulations are coming and will be a significant focus for lawmakers in the U.S. and globally in 2022. That's according to Beena Ammanath, executive director of the Global Deloitte AI Institute, who sees a fast-moving worldwide push for AI regulation. As artificial intelligence technology use increases across enterprises, Ammanath said it will be important for governments, the private sector and consumer groups to develop regulations for AI and other emerging technologies. Broadly, advocates for AI regulation seek transparency for black box algorithms and the means to protect consumers from bias and discrimination. The U.S. has been slow to regulate AI compared to the U.K., Germany, China and Canada.