In IEEE TIFS 2023, Chen et al. proposed a method called APFed, which leverages additive homomorphic encryption to encrypt each client’s gradient, aiming to prevent information leakage while effectively defending against poisoning attacks. In this paper, we demonstrate a fundamental flaw in the authors’ claim of security proof yielding that the proposed APFed method is insecure.

In privacy-preserving machine learning (PPML), homomorphic encryption (HE) has emerged as a significant primitive, allowing the use of machine learning (ML) models while protecting the confidentiality of input data. Although extensive research has been conducted on implementing PPML with HE by developing the efficient construction of private counterparts to ML models, the efficient HE implementation of embedding layers for token inputs such as words remains inadequately addressed. Thus, our study proposes an efficient algorithm for privacy-preserving embedding via look-up table evaluation with HE(HELUT) by developing an encrypted indicator function (EIF) that assures high precision with the use of the approximate HE scheme(CKKS). Based on the proposed EIF, we propose the CodedHELUT algorithm to facilitate an encrypted embedding layer for the first time. CodedHELUT leverages coded inputs to improve overall efficiency and optimize memory usage. Our comprehensive empirical analysis encompasses both synthetic tables and real-world largescale word embedding models. CodedHELUT algorithm achieves amortized evaluation time of 0.018-0.242s for GloVe6B50d, 0.104-01.298s for GloVe42300d, 0.262-3.283s for GPT-2 and BERT embedding layers while maintaining high precision (16 bits)

In IEEE TIFS 2023, NTRU+ has been proposed, an efficient lattice-based post-quantum Key Encapsulation Mechanism (KEM), which has also been submitted to the KpqC competition. In this paper, we propose an effective classical chosen ciphertext attack to recover the transmitted session key for NTRU+ with all but negligible probability for the first time. With the proposed attacks, we show that all the suggested parameters of NTRU+ do not satisfy the claimed IND-CCA security. Moreover, we elaborate on some flaws in the security proof, a part of which introduces our attack. We also suggest a way to modify the NTRU+ scheme to defend our attack while maintaining its practical performance.

Post-quantum signature schemes based on the MPC-in-the-Head (MPCitH) paradigm are recently attracting significant attention as their security solely depends on the one-wayness of the underlying primitive, providing diversity for the hardness assumption in post-quantum cryptography. Recent MPCitH-friendly ciphers have been designed using simple algebraic S-boxes operating on a large field in order to improve the performance of the resulting signature schemes. Due to their simple algebraic structures, their security against algebraic attacks should be comprehensively studied.

Fair learning has received a lot of attention in recent years since machine learning models can be unfair in automated decision-making systems with respect to sensitive attributes such as gender, race, etc. However, to mitigate the discrimination on the sensitive attributes and train a fair model, most fair learning methods have required to get access to the sensitive attributes in training or validation phases. In this study, we propose a privacy-preserving training algorithm for a fair support vector machine classifier based on Homomorphic Encryption (HE), where the privacy of both sensitive information and model secrecy can be preserved. The expensive computational costs of HE can be significantly improved by protecting only the sensitive information, introducing refined formulation and low-rank approximation using shared eigenvectors. Through experiments on the synthetic and real-world data, we demonstrate the effectiveness of our algorithm in terms of accuracy and fairness and show that our method significantly outperforms other privacy-preserving solutions in terms of better trade-offs between accuracy and fairness. To the best of our knowledge, our algorithm is the first privacy-preserving fair learning algorithm using HE.

This paper derives the average bit error probability (BEP) for bandlimited hybrid SFH/DS-CDMA over an additive white Gaussian channel when overlapping of adjacent hopping bands is permitted in the frequency domain. The numerical results which focused on the gain by overlapping of the hopping bands are presented for DPSK and BFSK modulation/demodulation. The type of hit is categorised into five or eight hit types to represent a hit from a signal in adjacent hopping bands instead of the conventional two types of hits, i.e. partial and full hits.