Pre-trained language models (PLMs) have demonstrated significant proficiency in solving a wide range of general natural language processing (NLP) tasks. Researchers have observed a direct correlation between the performance of these models and their sizes. As a result, the sizes of these models have notably expanded in recent years, persuading researchers to adopt the term large language models (LLMs) to characterize the larger-sized PLMs. The size expansion comes with a distinct capability called in-context learning (ICL), which represents a special form of prompting and allows the models to be utilized through the presentation of demonstration examples without modifications to the model parameters. Although interesting, privacy concerns have become a major obstacle in its widespread usage. Multiple studies have examined the privacy risks linked to ICL and prompting in general, and have devised techniques to alleviate these risks. Thus, there is a necessity to organize these mitigation techniques for the benefit of the community. In this survey, we provide a systematic overview of the privacy protection methods employed during ICL and prompting in general. We review, analyze, and compare different methods under this paradigm. Furthermore, we provide a summary of the resources accessible for the development of these frameworks. Finally, we discuss the limitations of these frameworks and offer a detailed examination of the promising areas that necessitate further exploration.

The digitization of health records due to technological developments has paved the way for patients to be collaboratively treated by different healthcare institutions. In collaborative ehealth systems, a patient's health data is stored remotely in the cloud for sharing with different healthcare service providers. However, the use of third parties for storage exposes the data to several privacy and security violation threats. Ciphertext policy attribute-based encryption (CP-ABE) which provides a fine-grained access control is a promising solution to privacy and security issues in the cloud environment and as a result, it has been widely studied for secure sharing of health data in cloud-based ehealth systems. Addressing the aspects of expressiveness, efficiency, user collusion resistance and attribute/user revocation in CP-ABE have been at the forefront of these studies. Thus, in this study, we proposed a novel expressive, efficient and collusion resistant access control scheme with immediate attribute/user revocation for secure sharing of health data in collaborative ehealth systems. The proposed scheme additionally achieves forward and backward security. To realize these features, our access control is based on the ordered binary decision diagram (OBDD) access structure and it binds the user keys to the user identities. Security and performance analysis show that our proposed scheme is secure, expressive and efficient.

With the advancement of information and communication technology (ICT), the medical sector is undergoing a massive transformation. Health records are being digitized, stored remotely in the cloud and shared with different stakeholders. However, the use of the cloud for personal health record (PHR) storage presents data security and privacy challenges. Ciphertext-policy attribute-based encryption (CP-ABE) is being widely studied for fine-grained access control of PHRs in the cloud. Expressiveness, efficiency and attribute revocation, among others, are some key requirements of a cloud based health systems. But, many of the proposed CP-ABE schemes rely on access structures that are either restrictive or cumbersome and thus result in less expressive and efficient schemes. Many of the schemes also lack mechanisms for efficient and immediate attribute/user revocation. In this work, we propose an expressive and efficient access control scheme with attribute/user revocation based on ordered binary decision diagram (OBDD) access structure. We use the attribute group approach to achieve the attribute/user revocation in our work. Additionally, the ciphertexts and private keys are assigned version numbers to prevent the revoked group members from colluding with non-revoked members. Security and efficiency analysis show that our proposed scheme is secure, expressive and efficient.

Nowadays, the internet of things (IoT) is used to generate data in several application domains. A logistic regression, which is a standard machine learning algorithm with a wide application range, is built on such data. Nevertheless, building a powerful and effective logistic regression model requires large amounts of data. Thus, collaboration between multiple IoT participants has often been the go-to approach. However, privacy concerns and poor data quality are two challenges that threaten the success of such a setting. Several studies have proposed different methods to address the privacy concern but to the best of our knowledge, little attention has been paid towards addressing the poor data quality problems in the multi-party logistic regression model. Thus, in this study, we propose a multi-party privacy-preserving logistic regression framework with poor quality data filtering for IoT data contributors to address both problems. Specifically, we propose a new metric gradient similarity in a distributed setting that we employ to filter out parameters from data contributors with poor quality data. To solve the privacy challenge, we employ homomorphic encryption. Theoretical analysis and experimental evaluations using real-world datasets demonstrate that our proposed framework is privacy-preserving and robust against poor quality data.