Artificial Intelligence (AI) algorithms have become a critical tool for addressing the transient stability assessment issue in modern power systems. By leveraging historical or simulation data to establish correlation...
详细信息
ISBN:
(数字)9798331510107
ISBN:
(纸本)9798331510114
Artificial Intelligence (AI) algorithms have become a critical tool for addressing the transient stability assessment issue in modern power systems. By leveraging historical or simulation data to establish correlations between features and transient stability, AI eliminates the need for modeling and analyzing intricate physical mechanisms, thereby reducing problem complexity and enhancing computational efficiency. However, the black-box nature of AI introduces significant security risks. Malicious attackers can exploit vulnerabilities during the training process, embedding backdoors in the models to manipulate their outputs and potentially disrupt power system operations. This paper explores the feasibility of embedding backdoors in AI models for power systems transient stability classifier and proposes a data poisoning-based backdoor attack method tailored to these systems. A backdoor trigger is designed to exploit the difficulty of accessing system nodes, causing AI models to misclassify specific scenario samples. To counter such threats, detection schemes are developed at both the model and sample levels. Finally, the effectiveness of the proposed attack and detection methods is validated through a case study on a AI-driven transient stability classifier.
As the scale of larger enterprises continues to expand, the financial management work of various subsidiaries has also increased, which has brought certain benefits to the company, but there have also been some proble...
详细信息
The proceedings contain 34 papers. The special focus in this conference is on International conference on Complex Systems Design and Management. The topics include: Model Compression Method Based on Knowledge Distilli...
ISBN:
(纸本)9789819965106
The proceedings contain 34 papers. The special focus in this conference is on International conference on Complex Systems Design and Management. The topics include: Model Compression Method Based on Knowledge Distilling and Adversarial Learning;research on Hardware-in-the-Loop Simulation for Aircraft Electric Power System;an Assumption of R&D Method Driven by Model and data;research on the Model-Based process and Method for Aviation Equipment Requirement Demonstration;enterprise modeling for Architecture-Centric Production Systems Planning;model-Based Embedded Radar System Software Development and Verification;model-Based Design Method and Practice of Avionics System Architecture in Civil Aircraft;applying Systems Thinking and Architectural Thinking to Improve Model-Based Systems Engineering Practice: Concepts and Methodology;Top-Down Military System-of-Systems Design Using MBSE Based on UAF: A Case Study;a Generalized Reuse Framework for Systems Engineering;PRODEC-Based Task analysis for the Design of Semi-Automated Trains;Risk Assessment Method of Aircraft Engine Product Supply Chain Based on AHP analysis;Design of Ground Integrated Testing Equipment Based on MBSE;model Based analysis and Verification Method for Helicopter System Performance Requirements;A SysML-Based Architecture Framework for Helicopter;Design and modeling of Nuclear Power Inspection Robot Based on MBSE;A Novel MBSE-Based Design Method for Search and Rescue Humanoid Robots;Design Method of Task Meta-model of Avionics System Architecture Based on DM2;investigation of a Model-Based Approach to a Grid Fin System Design;architecture Design of Model-Based Land Combat Equipment System;the Research on the Task Scheduling and Optimization Technology for Flight Tests;research and Application of Model-Based Aircraft Complex Function analysis Method.
Retail price optimization is a critical challenge in contemporary commerce, requiring robust methodologies to balance profitability and market competitiveness. This study introduces a data-driven framework employing a...
详细信息
Learning the dynamics of spatiotemporal events is a fundamental problem. Neural point processes enhance the expressivity of point process models with deep neural networks. However, most existing methods only consider ...
详细信息
Learning the dynamics of spatiotemporal events is a fundamental problem. Neural point processes enhance the expressivity of point process models with deep neural networks. However, most existing methods only consider temporal dynamics without spatial modeling. We propose Deep Spatiotemporal Point process (DeepSTPP), a deep dynamics model that integrates spatiotemporal point processes. Our method is flexible, efficient, and can accurately forecast irregularly sampled events over space and time. The key construction of our approach is the nonparametric space-time intensity function, governed by a latent process. The intensity function enjoys closed form integration for the density. The latent process captures the uncertainty of the event sequence. We use amortized variational inference to infer the latent process with deep networks. Using synthetic datasets, we validate our model can accurately learn the true intensity function. On real-world benchmark datasets, our model demonstrates superior performance over state-of-the-art baselines. Our code and data can be found at the link.
Recommender systems can significantly benefit from the availability of pre-trained large language models (LLMs), which can serve as a basic mechanism for generating recommendations based on detailed user and item data...
详细信息
ISBN:
(纸本)9798400705052
Recommender systems can significantly benefit from the availability of pre-trained large language models (LLMs), which can serve as a basic mechanism for generating recommendations based on detailed user and item data, such as text descriptions, user reviews, and metadata. On the one hand, this new generation of LLM-based recommender systems paves the way for dealing with traditional limitations, such as cold-start and data sparsity. Still, on the other hand, this poses fundamental challenges for their accountability. Reproducing experiments in the new context of LLM-based recommender systems is challenging for several reasons. New approaches are published at an unprecedented pace, which makes difficult to have a clear picture of the main protocols and good practices in the experimental evaluation. Moreover, the lack of proper frameworks for LLM-based recommendation development and evaluation makes the process of benchmarking models complex and uncertain. In this work, we discuss the main issues encountered when trying to reproduce P5 (Pretrain, Personalized Prompt, and Prediction Paradigm), one of the first works unifying different recommendation tasks in a shared language modeling and natural language generation framework. Starting from this study, we have developed LaikaLLM, a framework for training and evaluating LLMs, specifically for the recommendation task. It has been used to perform several experiments to assess the impact of using different LLMs, different personalization strategies, and a novel set of more informative prompts on the overall performance of recommendations in a fully reproducible environment.
Today, location-based services have become prevalent in the mobile platform, where mobile apps provide specific services to a user based on his or her location. Unfortunately, mobile apps can aggressively harvest loca...
详细信息
Thermophysical properties are a key factor in controlling heat losses and as a result in assessing the building's energy efficiency. For control heat losses one of the main thermophysical characteristics is the sp...
详细信息
Variations in process variables is one of the major concern in industrial plants. This varation can have a significant impact on both the quality of the product and the performance of equipment, resulting in increased...
详细信息
The upper limb spasticity training device (ULSTraD) is a simulator designed to replicate various spasticity behaviors observed in patients with upper limb spasticity. Through a systematic development process involving...
详细信息
暂无评论