Transformer-based models like BERT and GPT have achieved state-of-the-art performance across a wide range of AI tasks but raise serious privacy concerns when deployed as cloud inference services. To address this, secure multi-party computation (MPC) is commonly employed, encrypting both user inputs and model parameters to enable inference without revealing any private information. However, existing MPC-based secure transformer inference protocols are predominantly designed under the semi-honest security model. Extending these protocols to support malicious security remains a significant challenge, primarily due to the substantial overhead introduced by securely evaluating complex non-linear functions required for adversarial resilience. We introduce Mosformer, the first maliciously secure three-party (3PC) inference framework that efficiently supports large transformers such as BERT and GPT. We first design constant-round comparison and lookup table protocols with malicious security, leveraging verifiable distributed point functions (VDPFs). Building on these, we develop a suite of 3PC protocols for efficient and secure evaluation of complex non-linear functions in transformers. Together with optimized modulus conversion, our approach substantially reduces the overhead of secure transformer inference while preserving model accuracy. Experimental results on the vanilla transformer block show that Mosformer achieves up to a 5.3× speedup and a 4.3× reduction in communication over prior maliciously secure protocols. Despite offering stronger security guarantees, Mosformer achieves comparable or even superior online performance to state-of-the-art semi-honest 2PC and 3PC frameworks, including BOLT (Oakland 2024), BumbleBee (NDSS 2025), SHAFT (NDSS 2025), and Ditto (ICML 2024), on full-scale models such as BERT and GPT-2.

Transformer models have received widespread attention in recent years. They have gradually replaced recurrent neural networks (RNNs) in natural language processing (NLP) and are widely used in tasks such as machine translation, text generation, and language understanding. Similarly, transformers have shown impressive results in computer vision (CV). However, their unique attention mechanism places high demands on the computational and storage resources of the hardware. Deploying transformers on edge computing platforms is challenging due to their complex data flow, intensive matrix calculations, and the need for high-precision nonlinear functions. To address these challenges, we propose reconfigurable transformer accelerator (RTA), a transformer hardware accelerator that uses low-bit-width prediction to achieve dynamic sparsity. RTA reduces resource consumption by performing sparse matrix multiplications using low-bit-width operations, while its reconfigurable design allows the sparse module to be used for high-precision large-bit-width matrix multiplications. We have also optimized the RTA computing pipeline to reduce resource usage and improve computational efficiency. Additionally, we incorporate feature sharing to enhance the resource utilization efficiency of the hardware accelerator. Experimental results on the transformer-base model show that RTA achieves an average performance of 994 GOPS and a digital signal processor (DSP) efficiency of 1412. Compared to state-of-the-art transformer accelerators, RTA achieves$1.37\sim 11.03\times $DSP efficiency.

Density-based clustering algorithms such as DBSCAN, are highly effective in handling large datasets and identifying clusters of arbitrary shapes, playing a crucial role in data analysis fields like outlier detection and social networks. Outsourcing DBSCAN to the cloud brings substantial benefits but also raises major privacy concerns regarding the private input data of data owners. Existing private DBSCAN methods often face challenges of inefficiency or potential privacy leakage, hindering their practical deployment. To address these challenges, we introduce FSS-DBSCAN, a three-server MPC platform designed for outsourced private density-based clustering using function secret sharing (FSS). This solution guarantees clustering quality equivalent to plaintext algorithms, ensures comprehensive privacy protection, and achieves top-tier efficiency. The high performance of FSS-DBSCAN is driven by two pivotal strategies. First, we devise an MPC-friendly DBSCAN algorithm that is highly compatible with efficient secret-sharing-based cryptographic protocols and benefits from GPU acceleration. Second, we construct novel FSS-based protocols tailored for complex operations integral to our DBSCAN variant, such as Euclidean distance comparison and point assignment, and further optimize their computation through tensorization techniques. We implement our platform as an extensible system on top of PyTorch that leverages GPU hardware acceleration for cryptographic and tensorized operations. These innovations enable FSS-DBSCAN to significantly outperform ppDBSCAN (AsiaCCS 2021), reducing the clustering time for 5000 samples to approximately 2 hours, achieving an$83.4\times $speed improvement.