Zero-shot information extraction (IE) aims to build IE systems from the unannotated text. It is challenging due to involving little human intervention. Challenging but worthwhile, zero-shot IE reduces the time and effort that data labeling takes. Recent efforts on large language models (LLMs, e.g., GPT-3, ChatGPT) show promising performance on zero-shot settings, thus inspiring us to explore prompt-based methods. In this work, we ask whether strong IE models can be constructed by directly prompting LLMs. Specifically, we transform the zero-shot IE task into a multi-turn question-answering problem with a two-stage framework (ChatIE). With the power of ChatGPT, we extensively evaluate our framework on three IE tasks: entity-relation triple extract, named entity recognition, and event extraction. Empirical results on six datasets across two languages show that ChatIE achieves impressive performance and even surpasses some full-shot models on several datasets (e.g., NYT11-HRL). We believe that our work could shed light on building IE models with limited resources.

We study the fair regression problem under the notion of Mean Parity (MP) fairness, which requires the conditional mean of the learned function output to be constant with respect to the sensitive attributes. We address this problem by leveraging reproducing kernel Hilbert space (RKHS) to construct the functional space whose members are guaranteed to satisfy the fairness constraints. The proposed functional space suggests a closed-form solution for the fair regression problem that is naturally compatible with multiple sensitive attributes. Furthermore, by formulating the fairness-accuracy tradeoff as a relaxed fair regression problem, we derive a corresponding regression function that can be implemented efficiently and provides interpretable tradeoffs. More importantly, under some mild assumptions, the proposed method can be applied to regression problems with a covariance-based notion of fairness. Experimental results on benchmark datasets show the proposed methods achieve competitive and even superior performance compared with several state-of-the-art methods.

Neural forecasting of spatiotemporal time series drives both research and industrial innovation in several relevant application domains. Graph neural networks (GNNs) are often the core component of the forecasting architecture. However, in most spatiotemporal GNNs, the computational complexity scales up to a quadratic factor with the length of the sequence times the number of links in the graph, hence hindering the application of these models to large graphs and long temporal sequences. While methods to improve scalability have been proposed in the context of static graphs, few research efforts have been devoted to the spatiotemporal case. To fill this gap, we propose a scalable architecture that exploits an efficient encoding of both temporal and spatial dynamics. In particular, we use a randomized recurrent neural network to embed the history of the input time series into high-dimensional state representations encompassing multi-scale temporal dynamics. Such representations are then propagated along the spatial dimension using different powers of the graph adjacency matrix to generate node embeddings characterized by a rich pool of spatiotemporal features. The resulting node embeddings can be efficiently pre-computed in an unsupervised manner, before being fed to a feed-forward decoder that learns to map the multi-scale spatiotemporal representations to predictions. The training procedure can then be parallelized node-wise by sampling the node embeddings without breaking any dependency, thus enabling scalability to large networks. Empirical results on relevant datasets show that our approach achieves results competitive with the state of the art, while dramatically reducing the computational burden.

Revoking personal private data is one of the basic human rights, which has already been sheltered by several privacy-preserving laws in many countries. However, with the development of data science, machine learning and deep learning techniques, this right is usually neglected or violated as more and more patients' data are being collected and used for model training, especially in intelligent healthcare, thus making intelligent healthcare a sector where technology must meet the law, regulations, and privacy principles to ensure that the innovation is for the common good. In order to secure patients' right to be forgotten, we proposed a novel solution by using auditing to guide the forgetting process, where auditing means determining whether a dataset has been used to train the model and forgetting requires the information of a query dataset to be forgotten from the target model. We unified these two tasks by introducing a new approach called knowledge purification. To implement our solution, we developed AFS, a unified open-source software, which is able to evaluate and revoke patients' private data from pre-trained deep learning models. We demonstrated the generality of AFS by applying it to four tasks on different datasets with various data sizes and architectures of deep learning networks. The software is publicly available at \url{https://github.com/JoshuaChou2018/AFS}.

Distributed machine learning paradigms, such as federated learning, have been recently adopted in many privacy-critical applications for speech analysis. However, such frameworks are vulnerable to privacy leakage attacks from shared gradients. Despite extensive efforts in the image domain, the exploration of speech privacy leakage from gradients is quite limited. In this paper, we explore methods for recovering private speech/speaker information from the shared gradients in distributed learning settings. We conduct experiments on a keyword spotting model with two different types of speech features to quantify the amount of leaked information by measuring the similarity between the original and recovered speech signals. We further demonstrate the feasibility of inferring various levels of side-channel information, including speech content and speaker identity, under the distributed learning framework without accessing the user's data.

With generative models proliferating at a rapid rate, there is a growing need for general purpose fake image detectors. In this work, we first show that the existing paradigm, which consists of training a deep network for real-vs-fake classification, fails to detect fake images from newer breeds of generative models when trained to detect GAN fake images. Upon analysis, we find that the resulting classifier is asymmetrically tuned to detect patterns that make an image fake. The real class becomes a sink class holding anything that is not fake, including generated images from models not accessible during training. Building upon this discovery, we propose to perform real-vs-fake classification without learning; i.e., using a feature space not explicitly trained to distinguish real from fake images. We use nearest neighbor and linear probing as instantiations of this idea. When given access to the feature space of a large pretrained vision-language model, the very simple baseline of nearest neighbor classification has surprisingly good generalization ability in detecting fake images from a wide variety of generative models; e.g., it improves upon the SoTA by +15.07 mAP and +25.90% acc when tested on unseen diffusion and autoregressive models.

Check out all the on-demand sessions from the Intelligent Security Summit here. Artificial intelligence (AI) has already made its way into our personal and professional lives. Although the term is frequently used to describe a wide range of advanced computer processes, AI is best understood as a computer system or technological process that is capable of simulating human intelligence or learning to perform tasks and calculations and engage in decision-making. Until recently, the traditional understanding of AI described machine learning (ML) technologies that recognized patterns and/or predicted behavior or preferences (also known as analytical AI). Recently, a different kind of AI is revolutionizing the creative process -- generative artificial intelligence (GAI).

Law Minister Rijiju pitches for institutional arbitration; says AI can help arbitrators Law Minister Kiren Rijiju on Sunday batted for institutional arbitration in the country and pointed at loopholes in “ad hoc” arbitration, saying such proceedings are susceptible to court interventions which delay the final outcome. He also said artificial intelligence (AI) can help arbitrators in tasks such as document review and analysis, legal research, and drafting of awards. Addressing a Delhi Arbitration Weekend event at the Delhi High Court, he said majority of the people go for “ad hoc” arbitrations where the proceedings are not governed by pre-determined rules. As a result, these proceedings are susceptible to court intervention at various stages which leads to delay in final decision for the parties involved. On the other hand, Rijiju pointed out, institutional arbitrations are regulated by the rules of an institution that provide for a more structured and secure process. In addition, parties can benefit from the expertise of the arbitral institution having good quality infrastructure, he said. He said the government’s Vision 2030 is to see arbitration space remain dynamic, amendable to adopting best practices, as also conscious of the needs of time-bound and final adjudication of contractual disputes....

Fox News host Steve Hilton delves into ChatGPT, an artificial intelligence program that could have major implications for writing-focused jobs on'The Next Revolution.' Quickly evolving artificial intelligence technologies like ChatGPT could increase cyberattacks from foreign countries and displace workers in the U.S. labor force, highlighting the need for new skills and training among American students and workers, according to experts. Netra AI CEO Don Horan noted that artificial intelligence could be used to generate malicious code quickly by removing the algorithms' intended controls and creating content outside the authorized purview. He said that foreign acts can utilize tools like ChatGPT to improve espionage and accelerate elicitation, a process wherein a perpetrator gets to know a subject very well by gathering information and creating "the profile of a human being." This information is then used to force people to comply with their intended mission.

Welcome to the latest issue of your guide to AI, an editorialized newsletter covering key developments in AI research, industry, geopolitics and startups during January 2023. This one is a monster so it might get clipped in your inbox (read the online version in case!). Nathan wrote an oped in The Times for why university spinouts are a critical engine for our technology industry and why spinout policy needs urgent reform. The Times Higher Education profiled our open source data term database, spinout.fyi. Nathan commented on The Financial Times' Big Read on The growing tensions around spinouts at British universities. The State of AI Report provided two key figures to The Economist's piece on The race of the AI labs heats up. Register for next year's RAAIS, a full-day event in London that explores research frontiers and real-world applications of AI-first technology at the world's best companies. As usual, we love hearing what you're up to and what's on your mind, just hit reply or forward to your friends:-) BioNTech acquired London and Tunis-based AI startup InstaDeep for $680M (cash stock) - this was a huge deal.