Hong Liu

Federated learning, due to its distributed and privacy-protecting properties, is a good solution to the data silo problem in machine learning, but there are still many hidden dangers that threaten the security of federated learning, such as privacy leakage and potential malicious users. In this paper, we propose a federated learning copyright protection framework FedAaT. Our framework employs group signatures for authentication as well as user traceability, and reduces the computational cost of the server by aggregating signatures. To prevent models from being distributed maliciously, we introduce a conditional loss function to add traceability to local models.First, for the problem of difficult to verify the identity in the anonymity scenario of federated learning, considering that group signature has both anonymity and verifiability, a federated learning environment is organically combined with group signature, and a federated learning model copyright protection method based on group signature, FedAaT, is proposed.Second, to address the problem of excessive authentication overhead in federated learning scenarios, the process of authentication is optimized by introducing the aggregate signature technique, which reduces the computational overhead used for authentication by reducing the number of signatures that need to be verified.Finally, the problem of difficult traceability of illegally distributed models is addressed.For a specific set of inputs, we assign unique output sequences to each user and embed them into the model through a conditional loss function, and trace the model by detecting the output sequences.Experimental results show that our proposed FedAaT is effective in federated learning for authentication, user traceability, and reducing computational cost.

Dynamic searchable encryption methods allow a client to perform searches and updates over encrypted data stored in the cloud. However, existing researches show that the general dynamic searchable symmetric encryption (DSSE) scheme is vulnerable to statistical attacks due to the leakage of search patterns and access patterns. Although the traditional Oblivious Random Access Machine (ORAM) can hide the access pattern, it also incurs significant communication overhead and cannot hide the search pattern. To overcome this limitation, a DSSE scheme called obliviously shuffled incidence matrix DSSE (OSM-DSSE) is proposed in this paper to access the encrypted data obliviously without using ORAM. The OSM-DSSE scheme realizes efficient search and update operations based on an incidence matrix. In particular, a shuffling algorithm using Paillier encryption combines the 1-out-of-n obliviously transfer (OT) protocol to hide access pattern and an optimized padding scheme to obfuscate the search pattern with small storage overhead. Besides, a formalized security analysis and performance analysis of the proposed scheme is provided, which indicates that the OSM-DSSE scheme achieves high security, efficient searches, and low storage overhead. Also, this scheme not only completely hides the search and access patterns but also provides adaptive security against malicious attacks by adversaries. Furthermore, experimental results show that the OSM-DSSE scheme obtains 3-4x better execution efficiency than the state-of-art solutions.

With the development of cloud computing and cloud storage techniques, much attention has been focused on the privacy protection of outsourced data. Existing searchable encryption solutions can ensure the confidentiality and availability of data stored on the cloud. However, searchable encryption is vulnerable to statistical inference attacks, which exploit the disclosure of access patterns on encrypted indexes and encrypted file sets, which has become a potential way to reveal user privacy. Oblivious random access memory (ORAM) is an important means of concealing access patterns, yet its direct use in searchable encryptions is expensive. This paper presents a scheme for efficient and oblivious access to encrypted databases through encrypted indexes. This scheme is a hybrid ORAM scheme, which utilizes semi-homomorphic encryption to perform calculations in the ciphertext domain, overcoming the limitations of the huge overhead associated with Path-ORAM. For excessive amounts of data, semi-homomorphic encryption can significantly reduce communication and storage overhead. Our scheme can achieve high-security encrypted search and update operations at the same time. Moreover, the execution speed of ODS-Tree is 2-8x faster than that of ORAM-based schemes. In addition, the proposed scheme reduces the data block transmission and storage costs compared to existing frameworks.

Dynamic searchable encryption methods allow a client to perform searches and updates over encrypted data stored in the cloud. However, existing researches show that the general dynamic searchable symmetric encryption (DSSE) scheme is vulnerable to statistical attacks due to the leakage of search patterns and access patterns, which is detrimental to protecting the users’ privacy. Although the traditional Oblivious Random Access Machine (ORAM) can hide the access pattern, it also incurs significant communication overhead and cannot hide the search pattern. These limitations make it difficult to deploy the ORAM method in real cloud environments. To overcome this limitation, a DSSE scheme called obliviously shuffled incidence matrix DSSE (OSM-DSSE) is proposed in this paper to access the encrypted data obliviously. The OSM-DSSE scheme realizes efficient search and update operations based on an incidence matrix. In particular, a shuffling algorithm using Paillier encryption is combined with 1-out-of-n obliviously transfer (OT) protocol and local differential privacy to obfuscate the search targets. Besides, a formalized security analysis and performance analysis on the proposed scheme is provided, which indicates that the OSM-DSSE scheme achieves high security, efficient searches, and low storage overhead. Also, this scheme not only completely hides the search and access patterns but also provides adaptive security against malicious attacks by adversaries. Furthermore, experimental results show that the OSM-DSSE scheme obtains 3-4x better execution efficiency than the state-of-art solutions.