Cross-domain fake news detection aims to mitigate domain shift and improve detection performance by transferring knowledge across domains. Existing approaches transfer knowledge based on news content and user engagements from a source domain to a target domain. However, these approaches face two main limitations, hindering effective knowledge transfer and optimal fake news detection performance. Firstly, from a micro perspective, they neglect the negative impact of veracity-irrelevant features in news content when transferring domain-shared features across domains. Secondly, from a macro perspective, existing approaches ignore the relationship between user engagement and news content, which reveals shared behaviors of common users across domains and can facilitate more effective knowledge transfer. To address these limitations, we propose a novel macro- and micro- hierarchical transfer learning framework (MMHT) for cross-domain fake news detection. Firstly, we propose a micro-hierarchical disentangling module to disentangle veracity-relevant and veracity-irrelevant features from news content in the source domain for improving fake news detection performance in the target domain. Secondly, we propose a macro-hierarchical transfer learning module to generate engagement features based on common users' shared behaviors in different domains for improving effectiveness of knowledge transfer. Extensive experiments on real-world datasets demonstrate that our framework significantly outperforms the state-of-the-art baselines.

Transfer of knowledge across domains is the focus for cross-domain and multi-domain fake news detection. However, most of the existing methods based on cross-domain knowledge transfer have two issues: (1) they usually ignore domain-specific features; (2) they are less effective in handling the imbalanced data distribution across domains. Targeting these two issues, we focus on how to effectively leverage user-news engagements in both data-richer and data-sparser domains. This is because not only users' engagement characteristics closely relate to the veracity of the engaged news, but also there are consistent patterns in common users' engagements with news across domains. Considering these two insights, this work aims to perform dual-target cross-domain fake news detection via well modeling users' engagement patterns. In particular, it aims to transfer knowledge based on user-news engagements for handling the imbalanced data distribution across domains, which is novel but challenging. To this end, in this paper, we propose a novel framework to mine User-news engagement Patterns for DuAl-TargEt cross-domain fake news detection (UPDATE). In UPDATE, we first mine user-news engagement patterns as the key auxiliary information for cross-domain knowledge transfer. In such a way, it avoids the necessity to remove the domain-specific news information, and thereby, better preserve useful news information. Then, we combine engagement features of common users in both data-richer and data-sparser domains. By doing so, UPDATE improves the information richness in each of the two domains, thus improving detection performance in both domains when detecting news from domains with imbalanced data distribution. Extensive experiments conducted on real-world datasets demonstrate that UPDATE significantly outperforms state-of-the-art cross-domain and multi-domain methods as well as large language models (LLMs), such as GPT-3.5-turbo in terms of AUC and Fl-score for fake news detection.

Cloud computing has become prevalent due to its extensive storage resources and robust computational capacities. To protect data security and privacy, data owners opt for uploading encrypted data to the cloud. Flexible sharing of these encrypted data in a group of users is a critical functionality in cloud storage. In addition, given that users may exit the group, revocation becomes a crucial requirement in group data-sharing systems. The Key-Aggregate Cryptosystem (KAC) has become a promising mechanism for group data sharing. The decryption rights for any set of ciphertexts can be efficiently delegated by distributing a constant-size aggregate key, while the confidentiality of other ciphertexts outside the set is maintained. However, in previous KAC schemes, revocation remains a challenging task regarding key update, ciphertext re-encryption, and collision resistance. In this paper, we propose a Key-Aggregate Cryptosystem with User Revocation (KAC-UR) scheme to overcome this challenge. The KAC-UR scheme not only achieves flexible data sharing, but also can perform secure and efficient user revocation with properties including collision resistance, revocation without data owner-user communication, and constant ciphertext size. The KAC-UR scheme also enables the cloud server to perform partial decryption, thereby significantly alleviating the computational burden for users. The KAC-UR scheme is chosen plaintext attack secure under the decisional Bilinear Diffie-Hellman Exponent assumption.

Public key encryption with equality test (PKEET) is a variant of classical public key encryption (PKE) with the special functionality of an equality test, and can be used in many applications such as in keyword search on encrypted data and for efficient management by partitioning encrypted data in the cloud. Since the original proposal of Yang et al. (CT-RSA, 2010), several subsequent proposals to improve the efficiency or functionality of PKEET have been reported. We present a PKEET construction from generic assumptions in the random oracle model . In particular, whereas previous results require number-theoretic assumptions or strictly stronger generic assumptions such as the existence of secure hierarchical identity-based encryption, our proposal requires only the existence of cryptographic hash functions and secure PKE schemes satisfying a special property , called randomness extractability . Informally, randomness extractability means that one can recover the randomness used in a ciphertext when given a secret key corresponding to a public key for the ciphertext . We investigate the fact that PKE schemes satisfying this property can be designed by the Fujisaki-Okamoto (FO) transformation, which is the widely utilized method to obtain secure PKE schemes from basic cryptographic primitives in the random oracle model . As a result, in combination with the FO transformation, we obtain a PKEET construction in the random oracle model if there exist a one-way PKE scheme, a one-time secure symmetric key encryption scheme , collision-resistant and one-way hash functions , and a pseudorandom function. In this sense, we remark that our PKEET construction is derived from fundamental generic assumptions only.

Public-key encryption with keyword search (PEKS) enables users to search over encrypted data and retrieve target data efficiently. However, most of existing PEKS schemes are vulnerable to adversaries equipped with quantum computers in the near future, and even incur complex certificate management procedures due to the public key infrastructure (PKI). To this end, we propose a proxy-oriented identity-based encryption with keyword search (PO-IBEKS) scheme from lattices for cloud storage, which is post-quantum secure. In PO-IBEKS, an original data owner authorizes a proxy to encrypt sensitive data as well as corresponding keywords and upload ciphertexts to clouds, which alleviates the data processing burden on the original data owner. Besides, PO-IBEKS can resist inside keyword guessing attacks (IKGA) from misbehaved cloud servers by integrating the learning with errors (LWE) encryption and preimage sampleable function. Each entity in PO-IBEKS is identified with her/his recognizable information, thereby eliminating managing certificates. Formal security analysis proves that PO-IBEKS can achieve ciphertext indistinguishability, existential unforgeability, and delegation security. Experimental results demonstrate PO-IBEKS is much more practical when compared with existing schemes.

Public key encryption with equality test (PKEET), which was first introduced by Yang et al. (CT-RSA, 2010), has various applications including facilitating keyword search on encrypted data and partitioning encrypted data on the cloud. It can be also applied to manage personal health records on the internet. For these reasons, there have been improvements on earlier PKEET schemes in terms of performance and functionality. We present a semi-generic method for PKEET constructions, assuming only the existence of IND-CCA2 secure traditional public key encryption (PKE) schemes, the hardness of Computational Diffie-Hellman (CDH) problems, and random oracles. Our approach has several advantages; it enables us to understand requirements for the equality test functionality more clearly. Furthermore, our approach is quite general, in that if we change the underlying PKE scheme with the identity-based encryption (IBE) scheme (and we assume the hardness of Bilinear Diffie-Hellman problems instead of CDH), then we obtain the first IBE scheme with equality test (IBEET) satisfying analogous security arguments to those of PKEET. Although an IBEET construction was recently proposed, but we note that it satisfies only weak security requirements.