Secure multiparty computation (MPC) over Z2kis more efficient than computations over fields, and studying MPC protocols under malicious security has practical application value. Malicious security with a dishonest majority over rings remains challenging. The most popular approach is SPDZ2k, however, this is a specific protocol that does not support the transformation of any existing semi-honest MPC protocols into malicious security protocols. The zero knowledge proof (ZKP)-based compiler satisfies this requirement. Existing state-of-the-art protocols have logarithmic online communication overhead in terms of the circuit size |C|, and their direct application to rings is nontrivial as they were originally designed for finite fields. In this work, we investigate the communication overhead to develop malicious security protocols. We bridge the gap between malicious security with abort and semi-honest security, by constructing a “GMW-style” verification protocol to achieve malicious security in a dishonest majority setting. This approach incurs a constant online communication overhead by enhancing the machinery of zero-knowledge fully linear interactive oracle proof (zk-FLIOP). Additionally, we extend the zk-FLIOP to work over any ring by invoking reverse multiplication friendly embeddings (RMFEs). Our results show that the online communication complexity of the verification process depends on only the security parameter, the number of parties, and the ring size. Furthermore, for small-scale circuits over Z2, we designed a distributed lookup table argument where both the total communication complexity and the computational cost are independent of the circuit size but of the input wires.

The advent of deep learning has accelerated the development of facial manipulation techniques, particularly face-swapping and face attribute editing, raising serious concerns about privacy and identity-related misuse. Existing proactive defense methods predominantly target attribute editing and often generalize poorly to face-swapping models, making it difficult to provide effective protection across both tasks within a unified framework. To bridge this gap, we propose a generalized defense framework, Epoch-Adaptive Adversarial Perturbation Optimization (EA-APO). Specifically, EA-APO introduces a proactive defense mechanism that establishes optimal adversarial paths by optimizing perturbations on a white-box surrogate model to enhance adversarial transferability, and applies the resulting perturbations to source face images to disrupt both face swapping and face attribute editing, even against previously unseen target models in black-box settings. This approach mitigates identity feature tampering while adapting to changes in visual attributes and preserving high-quality adversarial examples. Experimental results show the generalization of our method across multiple face-swapping and attribute-editing models, including commercial ones, while also maintaining strong defense under various common post-processing operations and real-world social media transmission conditions, underscoring its potential for real-world deployment.

Distributed learning frameworks, which partition neural network models across multiple computing nodes, enhance efficiency in collaborative edge-cloud systems, but may also introduce new vulnerabilities to evasion attacks, often in the form of adversarial perturbations. In this work, we present a new threat model that explores the feasibility of generating universal adversarial perturbations (UAPs) when the attacker has access only to the edge portion of the model, consisting of its initial network layers. Unlike traditional attacks that require full model knowledge, our approach shows that adversaries can induce effective mispredictions in the unknown cloud component by manipulating key feature representations at the edge. Following the proposed threat model, we introduce both edge-only untargeted and targeted formulations of UAPs designed to control intermediate features before the split point. Our results on ImageNet demonstrate strong attack transferability to the unknown cloud part, and we compare the proposed method with classical white-box and black-box techniques, highlighting its effectiveness. Additionally, we analyze the capability of an attacker to achieve targeted adversarial effects with edge-only knowledge, revealing intriguing behaviors across multiple networks. By introducing the first adversarial attacks with edge-only knowledge in split inference, this work underscores the importance of addressing partial model access in adversarial robustness, encouraging further research in this area.

Recently, thumbnail-preserving encryption (TPE) has attracted significant attention because it maintains certain visual information in encrypted images, thereby achieving a trade-off between visual usability and privacy protection. However, existing TPE schemes utilize independent encryption between pixels, blocks, or channels, which results in excessive robustness and consequently introduces security vulnerabilities. To address this issue, we propose a triple-chain architecture to achieve sensitive TPE. This architecture integrates three interdependent encryption chains at the pixel, block, and channel levels, establishing cryptographic dependencies such that any minor modification to either the original or encrypted image leads to completely divergent encryption/decryption outcomes. Specifically, the architecture introduces three chained encryption mechanisms: (1) pixel-level chained encryption propagates encrypted pixels outputs as the part of subsequent inputs; (2) block-level hashing derives new keys from plaintext-key concatenations; and (3) channel-level dependencies are established via iterative key derivation. This cascading structure ensures cryptographic interdependency across all levels. The experimental results verify that the proposed architecture achieves sensitive TPE for the first time while preserving the TPE characteristics of visual usability and privacy protection.