Attackers inject the designed adversarial sample into the target recommendation system to achieve illegal goals,seriously affecting the security and reliability of the recommendation system.It is difficult for attacke...Attackers inject the designed adversarial sample into the target recommendation system to achieve illegal goals,seriously affecting the security and reliability of the recommendation system.It is difficult for attackers to obtain detailed knowledge of the target model in actual scenarios,so using gradient optimization to generate adversarial samples in the local surrogate model has become an effective black‐box attack strategy.However,these methods suffer from gradients falling into local minima,limiting the transferability of the adversarial samples.This reduces the attack's effectiveness and often ignores the imperceptibility of the generated adversarial samples.To address these challenges,we propose a novel attack algorithm called PGMRS‐KL that combines pre‐gradient‐guided momentum gradient optimization strategy and fake user generation constrained by Kullback‐Leibler divergence.Specifically,the algorithm combines the accumulated gradient direction with the previous step's gradient direction to iteratively update the adversarial samples.It uses KL loss to minimize the distribution distance between fake and real user data,achieving high transferability and imperceptibility of the adversarial samples.Experimental results demonstrate the superiority of our approach over state‐of‐the‐art gradient‐based attack algorithms in terms of attack transferability and the generation of imperceptible fake user data.展开更多
With the prevalence of the Web, most decision-makers are likely to use the Web to support their decision-making. Web-based technologies are leading a major stream of researching decision support systems (DSS). We prop...With the prevalence of the Web, most decision-makers are likely to use the Web to support their decision-making. Web-based technologies are leading a major stream of researching decision support systems (DSS). We propose a formal definition and a conceptual framework for Web-based open DSS (WODSS). The formal definition gives an overall view of WODSS, and the conceptual framework based on browser/broker/server computing mode employs the electronic market to mediate decision-makers and providers, and facilitate sharing and reusing of decision resources. We also develop an admitting model, a trading model and a competing model of electronic market in WODSS based on market theory in economics. These models reveal the key mechanisms that drive WODSS operate efficiently.展开更多
长尾现象在序列推荐系统中长期存在,包括长尾用户和长尾项目两个方面。虽然现有许多研究缓解了序列推荐系统中的长尾问题,但大部分只是单方面地关注长尾用户或长尾项目。然而,长尾用户和长尾项目问题常常同时存在,只考虑其中一方会导致...长尾现象在序列推荐系统中长期存在,包括长尾用户和长尾项目两个方面。虽然现有许多研究缓解了序列推荐系统中的长尾问题,但大部分只是单方面地关注长尾用户或长尾项目。然而,长尾用户和长尾项目问题常常同时存在,只考虑其中一方会导致另一方性能不佳,且未关注到长尾用户、长尾项目各自的信息匮乏问题。提出一种利用GRU双分支信息协同增强的长尾推荐模型(long-tail recommendation model utilizing gated recurrent unit dualbranch information collaboration enhancement,LT-GRU),从用户与项目两个方面共同缓解长尾问题,并通过协同增强的方式丰富长尾信息。该模型由长尾用户和长尾项目双分支组成,每个分支分别负责各自的信息处理,并相互训练以充实另一方的信息。同时,引入一种偏好机制,通过演算用户与项目的影响因子,以动态调整用户偏好与项目热度,进一步缓解长尾推荐中信息不足问题。在Amazon系列的6个真实数据集上与6种经典模型进行实验对比,相较于长尾推荐模型中最优的结果,所提模型LT-GRU在HR与NDCG两个指标上分别平均提高2.49%、3.80%。这表明,在不牺牲头部用户和热门项目推荐性能的情况下,有效地缓解了长尾用户和长尾项目问题。展开更多
基金The National Natural Science Foundation of China (61876001)Opening Foundation of State Key Laboratory of Cognitive Intelligence,Opening Foundation of State Key Laboratory of Cognitive Intelligence(iED2022-006)Scientific Research Planning Project of Anhui Province (2022AH050072)
文摘Attackers inject the designed adversarial sample into the target recommendation system to achieve illegal goals,seriously affecting the security and reliability of the recommendation system.It is difficult for attackers to obtain detailed knowledge of the target model in actual scenarios,so using gradient optimization to generate adversarial samples in the local surrogate model has become an effective black‐box attack strategy.However,these methods suffer from gradients falling into local minima,limiting the transferability of the adversarial samples.This reduces the attack's effectiveness and often ignores the imperceptibility of the generated adversarial samples.To address these challenges,we propose a novel attack algorithm called PGMRS‐KL that combines pre‐gradient‐guided momentum gradient optimization strategy and fake user generation constrained by Kullback‐Leibler divergence.Specifically,the algorithm combines the accumulated gradient direction with the previous step's gradient direction to iteratively update the adversarial samples.It uses KL loss to minimize the distribution distance between fake and real user data,achieving high transferability and imperceptibility of the adversarial samples.Experimental results demonstrate the superiority of our approach over state‐of‐the‐art gradient‐based attack algorithms in terms of attack transferability and the generation of imperceptible fake user data.
基金This project was supported by the Teaching and Research Award Fund for Outstanding Young Teachers in Higher Education Institutions of MOE.
文摘With the prevalence of the Web, most decision-makers are likely to use the Web to support their decision-making. Web-based technologies are leading a major stream of researching decision support systems (DSS). We propose a formal definition and a conceptual framework for Web-based open DSS (WODSS). The formal definition gives an overall view of WODSS, and the conceptual framework based on browser/broker/server computing mode employs the electronic market to mediate decision-makers and providers, and facilitate sharing and reusing of decision resources. We also develop an admitting model, a trading model and a competing model of electronic market in WODSS based on market theory in economics. These models reveal the key mechanisms that drive WODSS operate efficiently.
文摘长尾现象在序列推荐系统中长期存在,包括长尾用户和长尾项目两个方面。虽然现有许多研究缓解了序列推荐系统中的长尾问题,但大部分只是单方面地关注长尾用户或长尾项目。然而,长尾用户和长尾项目问题常常同时存在,只考虑其中一方会导致另一方性能不佳,且未关注到长尾用户、长尾项目各自的信息匮乏问题。提出一种利用GRU双分支信息协同增强的长尾推荐模型(long-tail recommendation model utilizing gated recurrent unit dualbranch information collaboration enhancement,LT-GRU),从用户与项目两个方面共同缓解长尾问题,并通过协同增强的方式丰富长尾信息。该模型由长尾用户和长尾项目双分支组成,每个分支分别负责各自的信息处理,并相互训练以充实另一方的信息。同时,引入一种偏好机制,通过演算用户与项目的影响因子,以动态调整用户偏好与项目热度,进一步缓解长尾推荐中信息不足问题。在Amazon系列的6个真实数据集上与6种经典模型进行实验对比,相较于长尾推荐模型中最优的结果,所提模型LT-GRU在HR与NDCG两个指标上分别平均提高2.49%、3.80%。这表明,在不牺牲头部用户和热门项目推荐性能的情况下,有效地缓解了长尾用户和长尾项目问题。
