Deep learning has successfully solved a wide range of tasks in 2D vision as a dominant AI technique. Recently, deep learning on 3D point clouds is becoming increasingly popular for addressing various tasks in this field. Despite remarkable achievements, deep learning algorithms are vulnerable to adversarial attacks. These attacks are imperceptible to the human eye but can easily fool deep neural networks in the testing and deployment stage. To encourage future research, this survey summarizes the current progress on adversarial attack and defense techniques on point cloud classification.This paper first introduces the principles and characteristics of adversarial attacks and summarizes and analyzes adversarial example generation methods in recent years. Additionally, it provides an overview of defense strategies, organized into data-focused and model-focused methods. Finally, it presents several current challenges and potential future research directions in this domain.

Accurate image reconstruction is at the heart of diagnostics in medical imaging. Supervised deep learning-based approaches have been investigated for solving inverse problems including image reconstruction. However, these trained models encounter unseen data distributions that are widely shifted from training data during deployment. Therefore, it is essential to assess whether a given input falls within the training data distribution for diagnostic purposes. Uncertainty estimation approaches exist but focus on providing an uncertainty map to radiologists, rather than assessing the training distribution fit. In this work, we propose a method based on the local Lipschitz-based metric to distinguish out-of-distribution images from in-distribution with an area under the curve of 99.94%. Empirically, we demonstrate a very strong relationship between the local Lipschitz value and mean absolute error (MAE), supported by a high Spearman's rank correlation coefficient of 0.8475, which determines the uncertainty estimation threshold for optimal model performance. Through the identification of false positives, the local Lipschitz and MAE relationship was used to guide data augmentation and reduce model uncertainty. Our study was validated using the AUTOMAP architecture for sensor-to-image Magnetic Resonance Imaging (MRI) reconstruction. We compare our proposed approach with baseline methods: Monte-Carlo dropout and deep ensembles, and further analysis included MRI denoising and Computed Tomography (CT) sparse-to-full view reconstruction using UNET architectures. We show that our approach is applicable to various architectures and learned functions, especially in the realm of medical image reconstruction, where preserving the diagnostic accuracy of reconstructed images remains paramount.

In the past couple of years, various approaches to representing and quantifying different types of predictive uncertainty in machine learning, notably in the setting of classification, have been proposed on the basis of second-order probability distributions, i.e., predictions in the form of distributions on probability distributions. A completely conclusive solution has not yet been found, however, as shown by recent criticisms of commonly used uncertainty measures associated with second-order distributions, identifying undesirable theoretical properties of these measures. In light of these criticisms, we propose a set of formal criteria that meaningful uncertainty measures for predictive uncertainty based on second-order distributions should obey. Moreover, we provide a general framework for developing uncertainty measures to account for these criteria, and offer an instantiation based on the Wasserstein distance, for which we prove that all criteria are satisfied.

We develop an NLP-based procedure for detecting systematic nonmeritorious consumer complaints, simply called systematic anomalies, among complaint narratives. While classification algorithms are used to detect pronounced anomalies, in the case of smaller and frequent systematic anomalies, the algorithms may falter due to a variety of reasons, including technical ones as well as natural limitations of human analysts. Therefore, as the next step after classification, we convert the complaint narratives into quantitative data, which are then analyzed using an algorithm for detecting systematic anomalies. We illustrate the entire procedure using complaint narratives from the Consumer Complaint Database of the Consumer Financial Protection Bureau.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. New York's prison system unfairly punished more than 2,000 prisoners after tests of suspected contraband substances falsely tested positive for drugs, according to a report released Thursday. In hundreds of cases, the prisoners had committed no offense, but the flawed results were used to put them in solitary confinement, halt family visits, or cancel parole hearings. The report by Inspector General Lucy Lang found that state prison staff failed to confirm the test results with an outside lab.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. City lawmakers in Brazil have enacted what appears to be the nation's first legislation written entirely by artificial intelligence -- even if they didn't know it at the time. The experimental ordinance was passed in October in the southern city of Porto Alegre and city councilman Ramiro Rosário revealed this week that it was written by a chatbot, sparking objections and raising questions about the role of artificial intelligence in public policy. Rosário told The Associated Press that he asked OpenAI's chatbot ChatGPT to craft a proposal to prevent the city from charging taxpayers to replace water consumption meters if they are stolen.

US Senators John Kennedy (R-LA) and Jeff Merkley (D-OR) introduced a bipartisan bill Wednesday to end involuntary facial recognition screening at airports. The Traveler Privacy Protection Act would block the Transportation Security Administration (TSA) from continuing or expanding its facial recognition tech program. It would also require the government agency to explicitly receive congressional permission to renew it, and it would have to dispose of all biometric data within three months. Senator Merkley described the TSA's biometric collection practices as the first steps toward an Orwellian nightmare. "The TSA program is a precursor to a full-blown national surveillance state," Merkley wrote in a news release.

Microsoft will take a non-voting, observer position on OpenAI's board, CEO Sam Altman said in his first official missive after taking back the reins of the company on Wednesday. The observer position means Microsoft's representative can attend OpenAI's board meetings and access confidential information, but it does not have voting rights on matters including electing or choosing directors. Microsoft CEO Satya Nadella, who had recruited Altman to Microsoft after Altman's ouster from OpenAI, had said earlier that governance at the ChatGPT maker needs to change. OpenAI announced a new initial board last week that consists of former Salesforce co-CEO Bret Taylor as chair and Larry Summers, former US treasury secretary. Quora CEO Adam D'Angelo, who was part of the board who fired Altman, also stayed on.

The Biden White House recently enacted its latest executive order designed to establish a guiding framework for generative artificial intelligence development -- including content authentication and using digital watermarks to indicate when digital assets made by the Federal government are computer generated. Here's how it and similar copy protection technologies might help content creators more securely authenticate their online works in an age of generative AI misinformation. Analog watermarking techniques were first developed in Italy in 1282. Papermakers would implant thin wires into the paper mold, which would create almost imperceptibly thinner areas of the sheet which would become apparent when held up to a light. Not only were analog watermarks used to authenticate where and how a company's products were produced, the marks could also be leveraged to pass concealed, encoded messages.

Over the course of two months from its debut in November 2022, ChatGPT exploded in popularity, from niche online curio to 100 million monthly active users -- the fastest user base growth in the history of the Internet. In less than a year, it has earned the backing of Silicon Valley's biggest firms, and been shoehorned into myriad applications from academia and the arts to marketing, medicine, gaming and government. In short ChatGPT is just about everywhere. Few industries have remained untouched by the viral adoption of the generative AI's tools. On the first anniversary of its release, let's take a look back on the year of ChatGPT that brought us here.