With the growing deployment of pre-trained models like Transformers on cloud platforms, privacy concerns about model parameters and inference data are intensifying. Existing Privacy-Preserving Transformer Inference (PPTI) frameworks face the “impossible trinity” of balancing privacy, efficiency, and performance: Secure Multi-Party Computation (SMPC)-based approaches ensure strong privacy but suffer from high computational overhead and performance losses; Conversely, permutation-based methods achieve near-plaintext efficiency and accuracy but compromise privacy by exposing sensitive model parameters and intermediate results. Bridging this gap with a single approach presents substantial challenges, motivating the introduction of CENTAUR, a groundbreaking PPTI framework that seamlessly integrates random permutations and SMPC to address the “impossible trinity”. By designing efficient PPTI algorithms tailored to the structural properties of Transformer models, CENTAUR achieves an unprecedented balance among privacy, efficiency, and performance. Our experiments demonstrate CENTAUR’s ability to resist diverse data reconstruction attacks, achieve plaintext-level inference accuracy, and boost inference speed by 5.0~30.4 times, unlocking new possibilities for secure and efficient AI deployment.

Federated learning (FL) emerges as a promising collaborative framework within the field of machine learning (ML), offering the potential to train ML models on sensitive real-world data while maintaining data privacy. The primary security concerns surrounding FL, particularly the protection of local gradients’ privacy and ensuring the correctness of aggregated gradients, have attracted growing attention in both industry and academia. Recently, Duet al. proposed SVHFL, a secure and verifiable hybrid FL system. In this context, the term “secure” means that SVHFL functions as a privacy-preserving federated learning (PPFL) system, capable of protecting the privacy of local gradients from being learned by the server (i.e., the aggregator) and the clients, and “verifiable” implies that SVHFL can achieve the aggregation verification, i.e., it guarantees the correctness of aggregated gradients returned by the server. However, in this article, we propose two attacks that compromise SVHFL, demonstrating that SVHFL cannot protect the privacy of local gradients from being learned by the server and the clients. We analyze the internal causes of these privacy breaches in SVHFL and propose alternative solutions to prevent such privacy leaks. We hope that the exposure of these security vulnerabilities will act as a catalyst to prevent similar incidents from occurring in the future design of PPFL systems.

Trustworthy artificial intelligence (TAI) has proven invaluable in curbing potential negative repercussions tied to AI applications. Within the TAI spectrum, federated learning (FL) emerges as a promising solution to safeguard personal information in distributed settings across a multitude of practical contexts. However, the realm of FL is not without its challenges. Especially worrisome are adversarial attacks targeting its algorithmic robustness and systemic confidentiality. Moreover, the presence of biases and opacity in prediction outcomes further complicates FL’s broader adoption. Consequently, there is a growing expectation for FL to instill trust. To address this, we chart out a comprehensive road-map for Trustworthy Federated Learning (TFL) and provide an overview of existing efforts across four pivotal dimensions: Privacy and Security , Robustness , Fairness , and Explainability . For each dimension, we identify potential pitfalls that might undermine TFL and present a curated selection of defensive strategies, enriched by a discourse on technical solutions tailored for TFL. Furthermore, we present potential challenges and future directions to be explored for in-depth TFL research with broader impacts.

Gaussian process regression (GPR) is a non-parametric model that has been used in many real-world applications that involve sensitive personal data (e.g., healthcare, finance, etc.) from multiple data owners. To fully and securely exploit the value of different data sources, this paper proposes a privacy-preserving GPR method based on secret sharing (SS), a secure multi-party computation (SMPC) technique. In contrast to existing studies that protect the data privacy of GPR via homomorphic encryption, differential privacy, or federated learning, our proposed method is more practical and can be used to preserve the data privacy of both the model inputs and outputs for various data-sharing scenarios (e.g., horizontally/vertically-partitioned data). However, it is non-trivial to directly apply SS on the conventional GPR algorithm, as it includes some operations whose accuracy and/or efficiency have not been well-enhanced in the current SMPC protocol. To address this issue, we derive a new SS-based exponentiation operation through the idea of “confusion-correction” and construct an SS-based matrix inversion algorithm based on Cholesky decomposition. More importantly, we theoretically analyze the communication cost and the security of the proposed SS-based operations. Empirical results show that our proposed method can achieve reasonable accuracy and efficiency under the premise of preserving data privacy.