Chen Lin

Yang Li, Mingxuan Luo, Yeyun Gong et al.

Supervised fine-tuning with synthesized instructions has been a common practice for adapting LLMs to domain-specific QA tasks. However, the synthesized instructions deviate from real user questions and expected answers. This study proposes a novel framework called DeepThink to generate high-quality instructions. DeepThink first generates a few seed questions to mimic actual user questions, simulates conversations to uncover the hidden user needs, and refines the answer by conversational contexts and the retrieved documents for more comprehensive answers. Experiments demonstrate that DeepThink achieves an average performance improvement of 7.92% compared to a GPT-4-turbo+RAG-based assistant on the real user test set in the advertising domain across dimensions such as relevance, completeness, clarity, accuracy, and actionability.

Zhili Chen, Xiaoli Kan, Shun Zhang et al.

With the rapid development of GPS enabled devices (smartphones) and location-based applications, location privacy is increasingly concerned. Intuitively, it is widely believed that location privacy can be preserved by publishing aggregated mobility data, such as the number of users in an area at some time. However, a recent attack shows that these aggregated mobility data can be exploited to recover individual trajectories. In this paper, we first propose two differentially private basic schemes for aggregated mobility data publication, namely direct perturbation and threshold perturbation, which preserve location privacy of users and especially resist the trajectory recovery attack. Then, we explore the moving characteristics of mobile users, and design an improved scheme named static hybrid perturbation by combining the two basic schemes according to the moving characteristics. Since static hybrid perturbation works only for static data, which are entirely available before publishing, we further adapt the static hybrid perturbation by combining it with linear regression, and yield another improved scheme named dynamic hybrid perturbation. The dynamic hybrid perturbation works also for dynamic data, which are generated on the fly during publication. Privacy analysis shows that the proposed schemes achieve differential privacy. Extensive experiments on both simulated and real datasets demonstrate that all proposed schemes resist the trajectory recovery attack well, and the improved schemes significantly outperform the basic schemes.

Zhili Chen, Yu Wang, Shun Zhang et al.

Collaborative filtering (CF) recommendation algorithms are well-known for their outstanding recommendation performances, but previous researches showed that they could cause privacy leakage for users due to k-nearest neighboring (KNN) attacks. Recently, the notion of differential privacy (DP) has been applied to privacy preservation for collaborative filtering recommendation algorithms. However, as far as we know, existing differentially private CF recommendation schemes degraded the recommendation performance (such as recall and precision) to an unacceptable level. In this paper, in order to address the performance degradation problem, we propose a differentially private user-based collaborative filtering recommendation scheme based on k-means clustering (KDPCF). Specifically, to improve the recommendation performance, we first cluster the dataset into categories by k-means clustering and appropriately adjust the size of the target category to which the target user belongs, so that only users in the well-sized target category can be used for recommendations. Then we efficiently select a set of neighbors from the target category at one time by employing only one exponential mechanism instead of the composition of multiple ones, and base on the neighbor set to recommend. We theoretically prove that our scheme achieves differential privacy. Empirically, we use the MovieLens dataset to evaluate our recommendation system. The experimental results demonstrate a significant performance gain compared to existing schemes.