Finding intersections across sensitive data is a core operation in many real-world data-driven applications, such as healthcare, anti-money laundering, financial fraud, or watchlist applications. These applications often require large-scale collaboration across thousands or more independent sources, such as hospitals, financial institutions, or identity bureaus, where all records must remain encrypted during storage and computation, and are typically outsourced to dedicated/cloud servers. Such a highly distributed, large-scale, and encrypted setting makes it very challenging to apply existing solutions, e.g., (multi-party) private set intersection (PSI) or private membership test (PMT).

With the extensive deployment of biometric authentication systems, the need for biometric template protection (BTP) has been widely recognized. Designing a secure yet efficient BTP is still a long-lasting challenge, and locality-sensitive hashing (LSH) is a promising building block for designing BTPs. In this study, we propose a novel pre-image attack applicable to lots of existing LSH-based BTPs, showing that many of them are in factreversible. Our attack leverages structural properties shared by several LSH-based BTPs. Through investigation, we formalize a certain class of LSHs vulnerable to our attack, calledPMA-LSH, which contains several known LSH-based BTPs, even not-yet-cryptanalyzed ones. Furthermore, the recovered pre-image from our attack is much closer to the original template compared to previous attacks, facilitating recovery of the original biometrics via reconstruction attacks. With existing reconstruction methods, we successfully recovered biometrics from templates protected by several LSH-based BTPs. The recovered biometrics sufficiently resemble the original ones, so they can be further exploited to impersonate other recognition systems, including commercial APIs. To facilitate further study, our source code is publicly available athttps://github.com/Cryptology-Algorithm-Lab/Analysis_LSH.

As face recognition systems (FRS) become more widely used, user privacy becomes more important. A key privacy issue in FRS is protecting the user's face template, as the characteristics of the user's face image can be recovered from the template. Although recent advances in cryptographic tools such as homomorphic encryption (HE) have provided opportunities for securing the FRS, HE cannot be used directly with FRS in an efficient plug-and-play manner. In particular, although HE is functionally complete for arbitrary programs, it is basically designed for algebraic operations on encrypted data of predetermined shape, such as a polynomial ring. Thus, a non-tailored combination of HE and the system can yield very inefficient performance, and many previous HE-based face template protection methods are hundreds of times slower than plain systems without protection. In this study, we propose IDFace, a new HE-based secure and efficient face identification method with template protection. IDFace is designed on the basis of two novel techniques for efficient searching on a (homomorphically encrypted) biometric database with an angular metric. The first technique is a template representation transformation that sharply reduces the unit cost for the matching test. The second is a space-efficient encoding that reduces wasted space from the encryption algorithm, thus saving the number of operations on encrypted templates. Through experiments, we show that IDFace can identify a face template from among a database of 1M encrypted templates in 126ms, showing only 2X overhead compared to the identification over plaintexts.

Adversarial attacks on face recognition systems (FRSs) pose serious security and privacy threats, especially when these systems are used for identity verification. In this paper, we propose a novel method for generating adversarial faces—synthetic facial images that are visually distinct yet recognized as a target identity by the FRS. Unlike iterative optimization-based approaches (e.g., gradient descent or other iterative solvers), our method leverages the structural characteristics of the FRS feature space. We figure out that individuals sharing the same attribute (e.g., gender or race) form an attributed subsphere. By utilizing such subspheres, our method achieves both non-adaptiveness and a remarkably small number of queries. This eliminates the need for relying on transferability and open-source surrogate models, which have been a typical strategy when repeated adaptive queries to commercial FRSs are impossible. Despite requiring only a single non-adaptive query consisting of 100 face images, our method achieves a high success rate of over 93% against AWS’s CompareFaces API at its default threshold. Furthermore, unlike many existing attacks that perturb a given image, our method can deliberately produce adversarial faces that impersonate the target identity while exhibiting high-level attributes chosen by the adversary.