The detection of energy thefts is vital for the safety of the whole smart grid system. However, the detection alone is not enough since energy thefts can crucially affect the electricity supply leading to some blackouts. Moreover, privacy is one of the major challenges that must be preserved when dealing with clients' energy data. This is often overlooked in energy theft detection research as most current detection techniques rely on raw, unencrypted data, which may potentially expose sensitive and personal data. To solve this issue, we present a privacy-preserving energy theft detection technique with effective demand management that employs two layers of privacy protection. We explore a split learning mechanism that trains a detection model in a decentralised fashion without the need to exchange raw data. We also employ a second layer of privacy by the use of a masking scheme to mask clients' outputs in order to prevent inference attacks. A privacy-enhanced version of this mechanism also employs an additional layer of privacy protection by training a randomisation layer at the end of the client-side model. This is done to make the output as random as possible without compromising the detection performance. For the energy theft detection part, we design a multi-output machine learning model to identify energy thefts, estimate their volume, and effectively predict future demand. Finally, we use a comprehensive set of experiments to test our proposed scheme. The experimental results show that our scheme achieves high detection accuracy and greatly improves the privacy preservation degree.
相關內容
We describe a proof-of-concept development and application of a phase averaging technique to the nonlinear rotating shallow water equations on the sphere, discretised using compatible finite element methods. Phase averaging consists of averaging the nonlinearity over phase shifts in the exponential of the linear wave operator. Phase averaging aims to capture the slow dynamics in a solution that is smoother in time (in transformed variables) so that larger timesteps may be taken. We overcome the two key technical challenges that stand in the way of studying the phase averaging and advancing its implementation: 1) we have developed a stable matrix exponential specific to finite elements and 2) we have developed a parallel finite averaging proceedure. Following Peddle et al (2019), we consider finite width phase averaging windows, since the equations have a finite timescale separation. In our numerical implementation, the averaging integral is replaced by a Riemann sum, where each term can be evaluated in parallel. This creates an opportunity for parallelism in the timestepping method, which we use here to compute our solutions. Here, we focus on the stability and accuracy of the numerical solution. We confirm there is an optimal averaging window, in agreement with theory. Critically, we observe that the combined time discretisation and averaging error is much smaller than the time discretisation error in a semi-implicit method applied to the same spatial discretisation. An evaluation of the parallel aspects will follow in later work.
Most supervised learning methods assume that the data used in the training phase comes from the target population. However, in practice, one often faces dataset shift, which, if not adequately taken into account, may decrease the performance of their predictors. In this work, we propose a novel and flexible framework called DetectShift that enables quantification and testing of various types of dataset shifts, including shifts in the distributions of $(X, Y)$, $X$, $Y$, $X|Y$, and $Y|X$. DetectShift provides practitioners with insights about changes in their data, allowing them to leverage source and target data to retrain or adapt their predictors. That is particularly valuable in scenarios where labeled samples from the target domain are scarce. The framework utilizes test statistics with the same nature to quantify the magnitude of the various shifts, making results more interpretable. Moreover, it can be applied in both regression and classification tasks, as well as to different types of data such as tabular, text, and image data. Experimental results demonstrate the effectiveness of DetectShift in detecting dataset shifts even in higher dimensions. Our implementation for DetectShift can be found in //github.com/felipemaiapolo/detectshift.
Understanding superfluidity remains a major goal of condensed matter physics. Here we tackle this challenge utilizing the recently developed Fermionic neural network (FermiNet) wave function Ansatz for variational Monte Carlo calculations. We study the unitary Fermi gas, a system with strong, short-range, two-body interactions known to possess a superfluid ground state but difficult to describe quantitively. We demonstrate key limitations of the FermiNet Ansatz in studying the unitary Fermi gas and propose a simple modification that outperforms the original FermiNet significantly, giving highly accurate results. We prove mathematically that the new Ansatz is a strict generalization of the original FermiNet architecture, despite the use of fewer parameters. Our approach shares several advantanges with the FermiNet: the use of a neural network removes the need for an underlying basis set; and the flexiblity of the network yields extremely accurate results within a variational quantum Monte Carlo framework that provides access to unbiased estimates of arbitrary ground-state expectation values. We discuss how the method can be extended to study other superfluids.
This paper presents Squid, a new conjunctive query synthesis algorithm for searching code with target patterns. Given positive and negative examples along with a natural language description, Squid analyzes the relations derived from the examples by a Datalog-based program analyzer and synthesizes a conjunctive query expressing the search intent. The synthesized query can be further used to search for desired grammatical constructs in the editor. To achieve high efficiency, we prune the huge search space by removing unnecessary relations and enumerating query candidates via refinement. We also introduce two quantitative metrics for query prioritization to select the queries from multiple candidates, yielding desired queries for code search. We have evaluated Squid on over thirty code search tasks. It is shown that Squid successfully synthesizes the conjunctive queries for all the tasks, taking only 2.56 seconds on average.
Complex event processing (CEP) is a powerful and increasingly more important tool to analyse data streams for Internet of Things (IoT) applications. These data streams often contain private information that requires proper protection. However, privacy protection in CEP systems is still in its infancy, and most existing privacy-preserving mechanisms (PPMs) are adopted from those designed for data streams. Such approaches undermine the quality of the entire data stream and limit the performance of IoT applications. In this paper, we attempt to break the limitation and establish a new foundation for PPMs of CEP by proposing a novel pattern-level differential privacy (DP) guarantee. We introduce two PPMs that guarantee pattern-level DP. They operate only on data that correlate with private patterns rather than on the entire data stream, leading to higher data quality. One of the PPMs provides adaptive privacy protection and brings more granularity and generalization. We evaluate the performance of the proposed PPMs with two experiments on a real-world dataset and on a synthetic dataset. The results of the experiments indicate that our proposed privacy guarantee and its PPMs can deliver better data quality under equally strong privacy guarantees, compared to multiple well-known PPMs designed for data streams.
Federated learning involves training statistical models over edge devices such as mobile phones such that the training data is kept local. Federated Learning (FL) can serve as an ideal candidate for training spatial temporal models that rely on heterogeneous and potentially massive numbers of participants while preserving the privacy of highly sensitive location data. However, there are unique challenges involved with transitioning existing spatial temporal models to decentralized learning. In this survey paper, we review the existing literature that has proposed FL-based models for predicting human mobility, traffic prediction, community detection, location-based recommendation systems, and other spatial-temporal tasks. We describe the metrics and datasets these works have been using and create a baseline of these approaches in comparison to the centralized settings. Finally, we discuss the challenges of applying spatial-temporal models in a decentralized setting and by highlighting the gaps in the literature we provide a road map and opportunities for the research community.
We develop multilevel methods for interface-driven multiphysics problems that can be coupled across dimensions and where complexity and strength of the interface coupling deteriorates the performance of standard methods. We focus on solvers based on aggregation-based algebraic multigrid methods with custom smoothers that preserve the coupling information on each coarse level. We prove that with the proper choice of subspace splitting we obtain uniform convergence in discretization and physical parameters in the two-level setting. Additionally, we show parameter robustness and scalability with regards to number of the degrees of freedom of the system on several numerical examples related to the biophysical processes in the brain, namely the electric signalling in excitable tissue modeled by bidomain, EMI and reduced EMI equations.
We propose a novel approach for developing privacy-preserving large-scale recommender systems using differentially private (DP) large language models (LLMs) which overcomes certain challenges and limitations in DP training these complex systems. Our method is particularly well suited for the emerging area of LLM-based recommender systems, but can be readily employed for any recommender systems that process representations of natural language inputs. Our approach involves using DP training methods to fine-tune a publicly pre-trained LLM on a query generation task. The resulting model can generate private synthetic queries representative of the original queries which can be freely shared for any downstream non-private recommendation training procedures without incurring any additional privacy cost. We evaluate our method on its ability to securely train effective deep retrieval models, and we observe significant improvements in their retrieval quality without compromising query-level privacy guarantees compared to methods where the retrieval models are directly DP trained.
Bid optimization for online advertising from single advertiser's perspective has been thoroughly investigated in both academic research and industrial practice. However, existing work typically assume competitors do not change their bids, i.e., the wining price is fixed, leading to poor performance of the derived solution. Although a few studies use multi-agent reinforcement learning to set up a cooperative game, they still suffer the following drawbacks: (1) They fail to avoid collusion solutions where all the advertisers involved in an auction collude to bid an extremely low price on purpose. (2) Previous works cannot well handle the underlying complex bidding environment, leading to poor model convergence. This problem could be amplified when handling multiple objectives of advertisers which are practical demands but not considered by previous work. In this paper, we propose a novel multi-objective cooperative bid optimization formulation called Multi-Agent Cooperative bidding Games (MACG). MACG sets up a carefully designed multi-objective optimization framework where different objectives of advertisers are incorporated. A global objective to maximize the overall profit of all advertisements is added in order to encourage better cooperation and also to protect self-bidding advertisers. To avoid collusion, we also introduce an extra platform revenue constraint. We analyze the optimal functional form of the bidding formula theoretically and design a policy network accordingly to generate auction-level bids. Then we design an efficient multi-agent evolutionary strategy for model optimization. Offline experiments and online A/B tests conducted on the Taobao platform indicate both single advertiser's objective and global profit have been significantly improved compared to state-of-art methods.
As data are increasingly being stored in different silos and societies becoming more aware of data privacy issues, the traditional centralized training of artificial intelligence (AI) models is facing efficiency and privacy challenges. Recently, federated learning (FL) has emerged as an alternative solution and continue to thrive in this new reality. Existing FL protocol design has been shown to be vulnerable to adversaries within or outside of the system, compromising data privacy and system robustness. Besides training powerful global models, it is of paramount importance to design FL systems that have privacy guarantees and are resistant to different types of adversaries. In this paper, we conduct the first comprehensive survey on this topic. Through a concise introduction to the concept of FL, and a unique taxonomy covering: 1) threat models; 2) poisoning attacks and defenses against robustness; 3) inference attacks and defenses against privacy, we provide an accessible review of this important topic. We highlight the intuitions, key techniques as well as fundamental assumptions adopted by various attacks and defenses. Finally, we discuss promising future research directions towards robust and privacy-preserving federated learning.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191