Federated Learning (FL) has emerged as a promising paradigm for training machine learning models across distributed devices while preserving their data privacy. However, the robustness of FL models against adversarial...
详细信息
Federated Learning (FL) has emerged as a promising paradigm for training machine learning models across distributed devices while preserving their data privacy. However, the robustness of FL models against adversarial data and model attacks, noisy updates, and label-flipped data issues remain a critical concern. In this paper, we present a systematic literature review using the PRISMA framework to comprehensively analyze existing research on robust FL. Through a rigorous selection process using six key databases (ACM Digital Library, IEEE Xplore, ScienceDirect, Springer, Web of Science, and Scopus), we identify and categorize 244 studies into eight themes of ensuring robustness in FL: objective regularization, optimizer modification, differential privacy employment, additional dataset requirement and decentralization orchestration, manifold, client selection, new aggregation algorithms, and aggregation hyperparameter tuning. We synthesize the findings from these themes, highlighting the various approaches and their potential gaps proposed to enhance the robustness of FL models. Furthermore, we discuss future research directions, focusing on the potential of hybrid approaches, ensemble techniques, and adaptive mechanisms for addressing the challenges associated with robust FL. This review not only provides a comprehensive overview of the state-of-the-art in robust FL but also serves as a roadmap for researchers and practitioners seeking to advance the field and develop more robust and resilient FL systems.
This State-of-the-Art Survey contains a selection of papers representing state-of-the-art results in the engineering of secure software-based Future Internet services and systems, produced by the NESSoS project resear...
详细信息
ISBN:
(数字)9783319074528
ISBN:
(纸本)9783319074511
This State-of-the-Art Survey contains a selection of papers representing state-of-the-art results in the engineering of secure software-based Future Internet services and systems, produced by the NESSoS project researchers. The engineering approach of the network of Excellence NESSoS, funded by the European Commission, is based on the principle of addressing security concerns from the very beginning in all software development phases, thus contributing to reduce the amount of software vulnerabilities and enabling the systematic treatment of security needs through the engineering process. The 15 papers included in this volume deal with the main NESSoS research areas: security requirements for Future Internet services; creating secure service architectures and secure service design; supporting programming environments for secure and composable services; enabling security assurance and integrating former results in a risk-aware and cost-aware software life-cycle.
The rapid development of Large Language Models (LLMs) creates new opportunities for recommender systems, especially by exploiting the side information (e.g., descriptions and analyses of items) generated by these mode...
详细信息
The rapid development of Large Language Models (LLMs) creates new opportunities for recommender systems, especially by exploiting the side information (e.g., descriptions and analyses of items) generated by these models. However, aligning this side information with collaborative information from historical interactions poses significant challenges. The inherent biases within LLMs can skew recommendations, resulting in distorted and potentially unfair user experiences. On the other hand, propensity bias causes side information to be aligned in such a way that it often tends to represent all inputs in a low-dimensional subspace, leading to a phenomenon known as dimensional collapse, which severely restricts the recommender system’s ability to capture user preferences and behaviours. To address these issues, we introduce a novel framework named Counterfactual LLM Recommendation (CLLMR). Specifically, we propose a spectrum-based side information encoder that implicitly embeds structural information from historical interactions into the side information representation, thereby circumventing the risk of dimension collapse. Furthermore, our CLLMR approach explores the causal relationships inherent in LLM-based recommender systems. By leveraging counterfactual inference, we counteract the biases introduced by LLMs. Extensive experiments demonstrate that our CLLMR approach consistently enhances the performance of various recommender models.
Multi-modal sarcasm detection involves determining whether a given multi-modal input conveys sarcastic intent by analyzing the underlying sentiment. Recently, vision large language models have shown remarkable success...
详细信息
Multi-modal sarcasm detection involves determining whether a given multi-modal input conveys sarcastic intent by analyzing the underlying sentiment. Recently, vision large language models have shown remarkable success on various of multi-modal tasks. Inspired by this, we systematically investigate the impact of vision large language models in zero-shot multi-modal sarcasm detection task. Furthermore, to capture different perspectives of sarcastic expressions, we propose a multi-view agent framework, S3 Agent, designed to enhance zero-shot multi-modal sarcasm detection by leveraging three critical perspectives: superficial expression, semantic information, and sentiment expression. Our experiments on the MMSD2.0 dataset, which involves six models and four prompting strategies, demonstrate that our approach achieves state-of-the-art performance. Our method achieves an average improvement of 13.2% in accuracy. Moreover, we evaluate our method on the text-only sarcasm detection task, where it also surpasses baseline approaches.
The ?rst SKLOIS Conference on informationsecurity and Cryptography(CISC 2005) was organized by the State keylaboratory of informationsecurity of the Chinese Academy of Sciences. It was held in Beijing, China, Decem...
详细信息
ISBN:
(数字)9783540324249
ISBN:
(纸本)9783540308553
The ?rst SKLOIS Conference on informationsecurity and Cryptography(CISC 2005) was organized by the State keylaboratory of informationsecurity of the Chinese Academy of Sciences. It was held in Beijing, China, December 15-17,2005andwassponsoredbytheInstituteofSoftware,theChineseAcademy of Sciences, the Graduate School of the Chinese Academy of Sciences and the National Science Foundation of China. The conference proceedings, represe- ing invited and contributed papers, are published in this volume of Springer’s Lecture Notes in computer Science (LNCS) series. The area of research covered by CISC has been gaining importance in recent years, and a lot of fundamental, experimental and applied work has been done, advancing the state of the art. The program of CISC 2005 covered numerous ?elds of research within the general scope of the conference. The International Program Committee of the conference received a total of 196 submissions (from 21 countries). Thirty-three submissions were selected for presentation as regular papers and are part of this volume. In addition to this track, the conference also hosted a short-paper track of 32 presentations that were carefully selected as well. All submissions were reviewed by experts in the relevant areas and based on their ranking and strict selection criteria the papers were selected for the various tracks. We note that stricter criteria were applied to papers co-authored by program committee members. We further note that, obviously, no member took part in in?uencing the ranking of his or her own submissions.
Non-overlapping Cross-domain Sequential Recommendation (NCSR) is the task that focuses on domain knowledge transfer without overlapping entities. Compared with traditional Cross-domain Sequential Recommendation (CSR),...
详细信息
Non-overlapping Cross-domain Sequential Recommendation (NCSR) is the task that focuses on domain knowledge transfer without overlapping entities. Compared with traditional Cross-domain Sequential Recommendation (CSR), NCSR poses several challenges: 1) NCSR methods often rely on explicit item IDs, overlooking semantic information among entities. 2) Existing CSR mainly relies on domain alignment for knowledge transfer, risking semantic loss during alignment. 3) Most previous studies do not consider the many-to-one characteristic, which is challenging because of the utilization of multiple source domains. Given the above challenges, we introduce the prompt learning technique for Many-to-one Non-overlapping Cross-domain Sequential Recommendation (MNCSR) and propose a Text-enhanced Co-attention Prompt Learning Paradigm (TCPLP). Specifically, we capture semantic meanings by representing items through text rather than IDs, leveraging natural language universality to facilitate cross-domain knowledge transfer. Unlike prior works that need to conduct domain alignment, we directly learn transferable domain information, where two types of prompts, i.e., domain-shared and domain-specific prompts, are devised, with a co-attention-based network for prompt encoding. Then, we develop a two-stage learning strategy, i.e., pre-train & prompt-tuning paradigm, for domain knowledge pre-learning and transferring, respectively. We conduct extensive experiments on three datasets and the experimental results demonstrate the superiority of our TCPLP. Our source codes have been publicly released.
暂无评论