Recent studies have demonstrated that local training data in Federated Learning can be recovered from gradients, which are called gradient inversion attacks. These attacks display powerful effects on either computer vision or natural language processing tasks. As it is known that there are certain correlations between multi-modality data, we argue that the threat of such attacks combined with Multi-modal Learning may cause more severe effects. Different modalities may communicate through gradients to provide richer information for the attackers, thus improving the strength and efficiency of the gradient inversion attacks. In this paper, we propose the Mutual Gradient Inversion Attack (MGIA), by utilizing the shared labels between image and text modalities combined with the idea of knowledge distillation. Our experimental results show that MGIA achieves the best quality of both modality data and label recoveries in comparison with other methods. In the meanwhile, MGIA verifies that multi-modality gradient inversion attacks are more likely to disclose private information than the existing single-modality attacks.

Payment channel network (PCN) is a promising off-chain technology for blockchain scalability, but it suffers from poor sustainability in practice. In other words, due to the imbalanced transfer in channels, the balance in one direction of channels gradually becomes exhausted until the PCN is rebalanced via a consensus-based rebalancing protocol, during which the involved channels must be suspended. This paper presents Cycle, the first off-chain protocol for a sustainable PCN. It not only keeps the PCN at a balanced level consistently but also avoids the channel freeze incurred by the rebalancing protocol, leading to minimum failed payments and sustained PCN service, respectively. Cycle achieves these benefits based on a novel idea of asynchronous rebalancing. During the normal off-chain running, the participants share the information about their payments and asynchronously rebalance the PCN following the principle that payments along circular channels can cancel each other out. To guarantee security, the protocol resolves the disputes resulting from network latency or malicious participants by a message mechanism for synchronization and a smart contract for arbitration. Moreover, to address the privacy concern during the information sharing, a truncated Laplace mechanism is designed to achieve differential privacy. Finally, we provide a proof-of-concept implementation in Ethereum, over which a real data-based simulation shows that Cycle satisfies 31% more payments than the state-of-the-art technique.

Recent studies have shown that the training samples can be recovered from gradients, which are called Gradient Inversion (GradInv) attacks. However, there remains a lack of extensive surveys covering recent advances and thorough analysis of this issue. In this paper, we present a comprehensive survey on GradInv, aiming to summarize the cutting-edge research and broaden the horizons for different domains. Firstly, we propose a taxonomy of GradInv attacks by characterizing existing attacks into two paradigms: iteration- and recursion-based attacks. In particular, we dig out some critical ingredients from the iteration-based attacks, including data initialization, model training and gradient matching. Second, we summarize emerging defense strategies against GradInv attacks. We find these approaches focus on three perspectives covering data obscuration, model improvement and gradient protection. Finally, we discuss some promising directions and open problems for further research.

The leakage of driving positions or traces poses a serious privacy threat upon the users in the vehicular ad-hoc networks (VANETs). A series of pseudonym changing approaches have been proposed to achieve unlinkability between the users' identities and their driving information. To investigate the effectiveness of the changing strategies on user anonymity, it is important to stand at the side of an adversary to implement posterior linking between different pseudonyms. In this paper, we remove the assumption of motion models commonly used in existing works, and propose a novel pseudonym linking scheme by focusing on the prediction of acceleration and direction angle. Further, we plug several side information (e.g., road structure, traffic signal) into the proposed scheme to improve the linking performance. Finally, based on five representative pseudonym changing strategies, extensive experiments are conducted to evaluate the performance of the proposed linking scheme. The experimental results show that the side-information assisted pseudonym linking scheme achieves success rates of over 74%.