arXiv subjects

Marcos A. Simplicio Jr

Publications and source records attributed to Marcos A. Simplicio Jr.

4 recordsLinked to original sources

arXiv2026

Lightweight, Practical Encrypted Face Recognition with GPU Support

Face recognition models operate in a client-server setting where a client extracts a compact face embedding and a server performs similarity search over a template database. This raises privacy concerns, as facial data is highly sensitive. To provide cryptographic privacy guarantees, one can use fully homomorphic encryption to perform end-to-end encrypted similarity search. However, existing FHE-based protocols are computationally costly and, impose high memory overhead. Building on prior work, HyDia (PoPETS 2025), we introduce algorithmic and system-level improvements targeting real-world deployment with resource-constrained clients. First, we propose BSGS-Diagonal, an algorithm delivering fast and memory-efficient similarity computation. BSGS-Diagonal substantially shrinks the rotation-key set, lowering both client and server memory requirements, and also improves practical server runtime. This yields a 91% reduction in the number of rotation keys, translating to approximately 14 GB less memory used on the client, and reducing overall CPU peak RAM from over 33 GB in the original HyDia to under 11 GB for databases up to size 1M. In addition, runtime is improved by up to 1.57x for the membership verification scenario and 1.43x for the identification scenario. Secondly, we introduce fully GPU-optimized similarity matrix computation kernels. The implementation is built upon FIDESlib, a CKKS-level GPU library based on OpenFHE. Rather than offloading individual CKKS primitives in isolation, the integrated kernels fuse operations to avoid repeated CPU-GPU ciphertext movement and costly FIDESlib/OpenFHE data-structure conversions. As a result, our GPU implementations of both HyDia and BSGS-Diagonal achieve up to 9x and 21x speedups, respectively, enabling sub-second encrypted face recognition for databases up to 32K entries while further reducing host memory usage.

cs.CR↗

arXiv2026

A UEFI System with SPDM to Protect Against Unauthorized Device Connections

Attackers willing to compromise computing systems can use malicious peripherals as an attack vector, threatening users that cannot verify the hardware's authenticity. To address this problem, our work uses the Security Protocol and Data Model to propose a UEFI system capable of authenticating PCIe and USB devices trying to connect with it. We also develop an open source proof-of-concept using emulation to evaluate and illustrate our proposal, which is capable of restricting the devices' connections to only those allowed, thus protecting the system against malicious peripherals. Then, using kernel virtualization features to evaluate the emulation, we collect the number of instructions and CPU cycles during boot. Our experiments reveal that, during firmware execution, the number of instructions and the number of CPU cycles increased respectively 13% and 8% on average. This processing overhead is acceptable in view of enhanced security. Institutions requiring high security levels can leverage our proof-of-concept to tailor their own system based on their own requirements.

cs.CR↗

arXiv2026

A Systematic Literature Review on LLM Defenses Against Prompt Injection and Jailbreaking: Expanding NIST Taxonomy

The rapid advancement and widespread adoption of generative artificial intelligence (GenAI) and large language models (LLMs) has been accompanied by the emergence of new security vulnerabilities and challenges, such as jailbreaking and other prompt injection attacks. These maliciously crafted inputs can exploit LLMs, causing data leaks, unauthorized actions, or compromised outputs, for instance. As both offensive and defensive prompt injection techniques evolve quickly, a structured understanding of mitigation strategies becomes increasingly important. To address that, this work presents the first systematic literature review on prompt injection mitigation strategies, comprehending 88 studies. Building upon NIST's report on adversarial machine learning, this work contributes to the field through several avenues. First, it identifies studies beyond those documented in NIST's report and other academic reviews and surveys. Second, we propose an extension to NIST taxonomy by introducing additional categories of defenses. Third, by adopting NIST's established terminology and taxonomy as a foundation, we promote consistency and enable future researchers to build upon the standardized taxonomy proposed in this work. Finally, we provide a comprehensive catalog of the reviewed prompt injection defenses, documenting their reported quantitative effectiveness across specific LLMs and attack datasets, while also indicating which solutions are open-source and model-agnostic. This catalog, together with the guidelines presented herein, aims to serve as a practical resource for researchers advancing the field of adversarial machine learning and for developers seeking to implement effective defenses in production systems.

cs.CR↗

arXiv2023

Benchmarking the Security Protocol and Data Model (SPDM) for component authentication

Efforts to secure computing systems via software traditionally focus on the operating system and application levels. In contrast, the Security Protocol and Data Model (SPDM) tackles firmware level security challenges, which are much harder (if at all possible) to detect with regular protection software. SPDM includes key features like enabling peripheral authentication, authenticated hardware measurements retrieval, and secure session establishment. Since SPDM is a relatively recent proposal, there is a lack of studies evaluating its performance impact on real-world applications. In this article, we address this gap by: (1) implementing the protocol on a simple virtual device, and then investigating the overhead introduced by each SDPM message; and (2) creating an SPDM-capable virtual hard drive based on VirtIO, and comparing the resulting read/write performance with a regular, unsecured implementation. Our results suggest that SPDM bootstrap time takes the order of tens of milliseconds, while the toll of introducing SPDM on hard drive communication highly depends on specific workload patterns. For example, for mixed random read/write operations, the slowdown is negligible in comparison to the baseline unsecured setup. Conversely, for sequential read or write operations, the data encryption process becomes the bottleneck, reducing the performance indicators by several orders of magnitude.

cs.CR↗