The digital transformation faces tremendous security challenges. In particular, the growing number of cyber-attacks targeting Internet of Things (IoT) systems restates the need for a reliable detection of malicious network activity. This paper presents a comparative analysis of supervised, unsupervised and reinforcement learning techniques on nine malware captures of the IoT-23 dataset, considering both binary and multi-class classification scenarios. The developed models consisted of Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Isolation Forest (iForest), Local Outlier Factor (LOF) and a Deep Reinforcement Learning (DRL) model based on a Double Deep Q-Network (DDQN), adapted to the intrusion detection context. The most reliable performance was achieved by LightGBM. Nonetheless, iForest displayed good anomaly detection results and the DRL model demonstrated the possible benefits of employing this methodology to continuously improve the detection. Overall, the obtained results indicate that the analyzed techniques are well suited for IoT intrusion detection.

Natural language communication is core to intelligence, as it allows ideas to be efficiently shared between humans or artificially intelligent systems. The generality of language allows us to express many intelligence tasks as taking in natural language input and producing natural language output. Autoregressive language modelling -- predicting the future of a text sequence from its past -- provides a simple yet powerful objective that admits formulation of numerous cognitive tasks. At the same time, it opens the door to plentiful training data: the internet, books, articles, code, and other writing. However this training objective is only an approximation to any specific goal or application, since we predict everything in the sequence rather than only the aspects we care about. Yet if we treat the resulting models with appropriate caution, we believe they will be a powerful tool to capture some of the richness of human intelligence. Using language models as an ingredient towards intelligence contrasts with their original application: transferring text over a limited-bandwidth communication channel. Shannon's Mathematical Theory of Communication (Shannon, 1948) linked the statistical modelling of natural language with compression, showing that measuring the cross entropy of a language model is equivalent to measuring its compression rate.

In this work, we study the emergence of sparsity and multiway structures in second-order statistical characterizations of dynamical processes governed by partial differential equations (PDEs). We consider several state-of-the-art multiway covariance and inverse covariance (precision) matrix estimators and examine their pros and cons in terms of accuracy and interpretability in the context of physics-driven forecasting when incorporated into the ensemble Kalman filter (EnKF). In particular, we show that multiway data generated from the Poisson and the convection-diffusion types of PDEs can be accurately tracked via EnKF when integrated with appropriate covariance and precision matrix estimators.

Today's battlefield environment is complex, dynamic and uncertain, and requires efficient support to ensure mission success. This relies on a proper support strategy to provide supported equipment able to fulfill the mission. In the context of defense where both systems and organization are complex, having a holistic approach is challenging by nature, forces and support agencies need to rely on an efficient decision support system. Logistics, readiness and sustainability are critical factors for asset management, which can benefit from AI to reach "Smart In Service" level relying especially on predictive and prescriptive approaches and on effective management of operational re-sources. Smart Support capacities can be then monitored by appropriate metrics and improved by multi-criteria decision support and knowledge management system. Depending on the operational context in terms of information and the objective, different AI paradigms (data-driven AI, knowledge-based AI) are suitable even a combination through hybrid AI.

We have created a knowledge graph based on major data sources used in ecotoxicological risk assessment. We have applied this knowledge graph to an important task in risk assessment, namely chemical effect prediction. We have evaluated nine knowledge graph embedding models from a selection of geometric, decomposition, and convolutional models on this prediction task. We show that using knowledge graph embeddings can increase the accuracy of effect prediction with neural networks. Furthermore, we have implemented a fine-tuning architecture which adapts the knowledge graph embeddings to the effect prediction task and leads to a better performance. Finally, we evaluate certain characteristics of the knowledge graph embedding models to shed light on the individual model performance.

This paper aims to help structure the risk landscape associated with large-scale Language Models (LMs). In order to foster advances in responsible innovation, an in-depth understanding of the potential risks posed by these models is needed. A wide range of established and anticipated risks are analysed in detail, drawing on multidisciplinary expertise and literature from computer science, linguistics, and social sciences. We outline six specific risk areas: I. Discrimination, Exclusion and Toxicity, II. Information Hazards, III. Misinformation Harms, V. Malicious Uses, V. Human-Computer Interaction Harms, VI. Automation, Access, and Environmental Harms. The first area concerns the perpetuation of stereotypes, unfair discrimination, exclusionary norms, toxic language, and lower performance by social group for LMs. The second focuses on risks from private data leaks or LMs correctly inferring sensitive information. The third addresses risks arising from poor, false or misleading information including in sensitive domains, and knock-on risks such as the erosion of trust in shared information. The fourth considers risks from actors who try to use LMs to cause harm. The fifth focuses on risks specific to LLMs used to underpin conversational agents that interact with human users, including unsafe use, manipulation or deception. The sixth discusses the risk of environmental harm, job automation, and other challenges that may have a disparate effect on different social groups or communities. In total, we review 21 risks in-depth. We discuss the points of origin of different risks and point to potential mitigation approaches. Lastly, we discuss organisational responsibilities in implementing mitigations, and the role of collaboration and participation. We highlight directions for further research, particularly on expanding the toolkit for assessing and evaluating the outlined risks in LMs.

In media news today, CNN and Chris Cuomo issue scathing statements against each other, the former anchor announces he's leaving his SiriusXM radio show, and a New York Times op-ed gets mocked for fearing free library is contributing to gentrification. Pollster Nate Silver on Monday savaged the analytics behind a recent Washington Post column claiming President Biden was being treated just as badly, or worse, by the media than former President Trump. In the piece published last week, liberal columnist Dana Milbank complained about Biden's media coverage being overly tough and implored journalists to do "soul-searching" and "think about what it is we're delivering to people." In a series of tweets, Silver argued the piece's "sentiment analysis" measuring the positivity and negativity of particular articles written about Trump and Biden was "complete crap," and gave examples to show how the data could be skewed more positively or negatively than it should have been. "To this good thread explaining why the'sentiment analysis' cited in the [Dana Milbank] WaPo article this weekend is complete crap--the analysis was used to make the claim that the press is just negative toward Biden as Trump--I'll also add a couple of comments based on their data," Silver wrote.

LOS ANGELES/WASHINGTON, Nov 15 (Thomson Reuters Foundation) - When the sheriff in Suffolk County, New York, requested $700,000 from the U.S. government for an artificial intelligence system to eavesdrop on prison phone conversations, his office called it a key tool in fighting gang-related and violent crime. But the county jail ended up listening to calls involving a much wider range of subjects - scanning as many as 600,000 minutes per month, according to public records from the county obtained by the Thomson Reuters Foundation. Beginning in 2019, Suffolk County was an early pilot site for the Verus AI-scanning system sold by California-based LEO Technologies, which uses Amazon speech-to-text technology to transcribe phone calls flagged by key word searches. The company and law enforcement officials say it is a crucial tool to keep prisons and jails safe, and fight crime, but critics say such systems trample the privacy rights of prisoners and other people, like family members, on the outside. "The ability to surveil and listen at scale in this rapid way - it is incredibly scary and chilling," said Julie Mao, deputy director at Just Futures Law, an immigration legal group.

Donald Trump and his former White House chief of staff Mark Meadows are peddling a new story about the ex-president's coronavirus infection. Their first story was that Trump didn't test positive until Oct. 1, 2020, two days after he debated Joe Biden. Then Meadows admitted in his new book, The Chief's Chief, that Trump actually tested positive on Sept. 26, three days before the debate. That admission was problematic, since Trump never informed Biden--or hundreds of other unwitting people who interacted closely with the maskless president in the intervening five days--about the test result. So now Trump and Meadows have concocted yet another story: The Sept. 26 result was a "false positive."

Elon Musk claims his Neuralink, a brain-interface technology company, is less than a year away from implanting chips into human brains. The news comes from the billionaire himself during a live-streamed interview with The Wall Street Journal CEO Council Summit on Monday, when asked about plans for the company in 2022. 'Neuralink's working well in monkeys and we're actually doing just a lot of testing and just confirming that it's very safe and reliable and the Neuralink device can be removed safely,' Musk said. 'We hope to have this in our first humans -- which will be people that have severe spinal cord injuries like tetraplegics, quadriplegics -- next year, pending FDA approval. 'I think we have a chance of being able to allow someone who cannot walk or use their arms be able to walk again – but not naturally.'