In place of in-house solutions, organizations are increasingly moving towards managed services for cyber defense. Security Operations Centers are specialized cybersecurity units responsible for the defense of an organization, but the large-scale centralization of threat detection is causing SOCs to endure an overwhelming amount of false positive alerts -- a phenomenon known as alert fatigue. Large collections of imprecise sensors, an inability to adapt to known false positives, evolution of the threat landscape, and inefficient use of analyst time all contribute to the alert fatigue problem. To combat these issues, we present That Escalated Quickly (TEQ), a machine learning framework that reduces alert fatigue with minimal changes to SOC workflows by predicting alert-level and incident-level actionability. On real-world data, the system is able to reduce the time it takes to respond to actionable incidents by $22.9\%$, suppress $54\%$ of false positives with a $95.1\%$ detection rate, and reduce the number of alerts an analyst needs to investigate within singular incidents by $14\%$.

We propose a novel graph-based approach for semantic parsing that resolves two problems observed in the literature: (1) seq2seq models fail on compositional generalization tasks; (2) previous work using phrase structure parsers cannot cover all the semantic parses observed in treebanks. We prove that both MAP inference and latent tag anchoring (required for weakly-supervised learning) are NP-hard problems. We propose two optimization algorithms based on constraint smoothing and conditional gradient to approximately solve these inference problems. Experimentally, our approach delivers state-of-the-art results on Geoquery, Scan and Clevr, both for i.i.d. splits and for splits that test for compositional generalization.

Deploying high-performance vision transformer (ViT) models on ubiquitous Internet of Things (IoT) devices to provide high-quality vision services will revolutionize the way we live, work, and interact with the world. Due to the contradiction between the limited resources of IoT devices and resource-intensive ViT models, the use of cloud servers to assist ViT model training has become mainstream. However, due to the larger number of parameters and floating-point operations (FLOPs) of the existing ViT models, the model parameters transmitted by cloud servers are large and difficult to run on resource-constrained IoT devices. To this end, this paper proposes a transmission-friendly ViT model, TFormer, for deployment on resource-constrained IoT devices with the assistance of a cloud server. The high performance and small number of model parameters and FLOPs of TFormer are attributed to the proposed hybrid layer and the proposed partially connected feed-forward network (PCS-FFN). The hybrid layer consists of nonlearnable modules and a pointwise convolution, which can obtain multitype and multiscale features with only a few parameters and FLOPs to improve the TFormer performance. The PCS-FFN adopts group convolution to reduce the number of parameters. The key idea of this paper is to propose TFormer with few model parameters and FLOPs to facilitate applications running on resource-constrained IoT devices to benefit from the high performance of the ViT models. Experimental results on the ImageNet-1K, MS COCO, and ADE20K datasets for image classification, object detection, and semantic segmentation tasks demonstrate that the proposed model outperforms other state-of-the-art models. Specifically, TFormer-S achieves 5% higher accuracy on ImageNet-1K than ResNet18 with 1.4$\times$ fewer parameters and FLOPs.

We introduce \`A-la-carte Prompt Tuning (APT), a transformer-based scheme to tune prompts on distinct data so that they can be arbitrarily composed at inference time. The individual prompts can be trained in isolation, possibly on different devices, at different times, and on different distributions or domains. Furthermore each prompt only contains information about the subset of data it was exposed to during training. During inference, models can be assembled based on arbitrary selections of data sources, which we call "\`a-la-carte learning". \`A-la-carte learning enables constructing bespoke models specific to each user's individual access rights and preferences. We can add or remove information from the model by simply adding or removing the corresponding prompts without retraining from scratch. We demonstrate that \`a-la-carte built models achieve accuracy within $5\%$ of models trained on the union of the respective sources, with comparable cost in terms of training and inference time. For the continual learning benchmarks Split CIFAR-100 and CORe50, we achieve state-of-the-art performance.

Correlated Equilibrium (CE) is a well-established solution concept that captures coordination among agents and enjoys good algorithmic properties. In real-world multi-agent systems, in addition to being in an equilibrium, agents' policies are often expected to meet requirements with respect to safety, and fairness. Such additional requirements can often be expressed in terms of the state density which measures the state-visitation frequencies during the course of a game. However, existing CE notions or CE-finding approaches cannot explicitly specify a CE with particular properties concerning state density; they do so implicitly by either modifying reward functions or using value functions as the selection criteria. The resulting CE may thus not fully fulfil the state-density requirements. In this paper, we propose Density-Based Correlated Equilibria (DBCE), a new notion of CE that explicitly takes state density as selection criterion. Concretely, we instantiate DBCE by specifying different state-density requirements motivated by real-world applications. To compute DBCE, we put forward the Density Based Correlated Policy Iteration algorithm for the underlying control problem. We perform experiments on various games where results demonstrate the advantage of our CE-finding approach over existing methods in scenarios with state-density concerns.

In 1992, Matt Moneymaker had an experience that would change his life. Some local farmers had told him about a number of mysterious sightings deep in the forests of Ohio. Without the internet or social media, Moneymaker did what you did back then: He placed classified ads in the hope that these witnesses might come forward and share their story and, crucially, the location where it had happened. "I went to the area where they had seen one, and I found tracks. And we heard their sounds, and I was at that point very, very, very committed to getting some video footage of these things" he told Engadget.

The survey results are published in McAfee's new'Modern Love' research report. As per the report, 65% of the total surveyed people prefer a machine-generated note in the style of e.e. cummings to his original 1952 poem I carry your heart with me. The most popular reason given for using AI as a writer to pen down love letters was that it would make the sender feel more confident. About 27% of the respondents feel this way. While 21% cited lack of time or lack of inspiration.

His attorney Ryan Abbott of Brown Neri Smith & Khan told Reuters on Wednesday that there is a "real financial importance to this case" that "might not have been so readily apparent a year and a half ago." LitigationcategoryThousands of J&J talc lawsuits in New Jersey get new judge, article with image EnvironmentcategoryMore than 100 lawsuits filed in U.S. court over Camp Lejeune water after waiting period passes, article with image EnvironmentcategoryMore than 100 lawsuits filed in U.S. court over Camp Lejeune water after waiting period passes, article with image Thaler has separately fought to obtain patents on behalf of his AI-invention system in 18 global jurisdictions. That effort has so far been unsuccessful in the U.S., UK, European Union and Australia. A UK Supreme Court hearing on Thaler's dispute there is set for March. Thaler's application named the system itself as the work's creator.

OpenAI's launch of ChatGPT in November 2022 has spurred a cascade of articles and commentary on artificial intelligence. The discussion, however, reveals how much artificial intelligence is already deployed. Artificial intelligence (AI) is one of those technologies with a long history of disappointment. Dating back to Alan Turing at the start of the theory of computing (or, more technically, computability), interest reached a high point with the development of "expert systems" in the early 1980s. These systems created great excitement about the possibilities of AI, but delivery was disappointing. As a result, histories of AI (see note) refer to the following period as the "AI Winter". Both major parties took policies supporting AI to the last federal election. A survey of voters, even knowledgeable ones, on policy commitments made for that election is unlikely to turn up AI as an important policy position. On the other hand, ChatGPT has been a big story for some of us, with suggestions that it can take over many jobs and concerns about the integrity of academic credentialing.

What is artificial intelligence (AI)? The term artificial intelligence (AI) describes computer-implemented approaches to emulate human decision-making structures to enable computers and machines to process and solve problems largely independently. An essential tool for being able to arrive at independent solutions is the ability of an AI system to learn. This ability is referred to as machine learning. In this process, the AI system learns because of examples to be able to generalize given patterns after the learning phase is complete.