Thi Hong Tran | Searcharxiv

arXiv2026

Transparent Identity Verification Approach Using MPC and Efficient Credential Status Handling

A secure and privacy-preserving identity verification process is essential for digital ecosys- tems. Current eKYC frameworks that rely on Zero-Knowledge Proofs (ZKPs) face high computational cost, rigid circuit design, complex integration, and expensive on-chain verification. The W3C 2021 BitString- based credential status mechanism also suffers from inefficient updates and poor scalability in large- scale deployments. We propose a transparent and cost-effective identity verification framework based on Multi-Party Computation (MPC). It enables private off-chain code execution and produces runtime proofs anchored to a blockchain. The framework introduces a multidimensional bit-matrix model with efficient compression. Using ZSTD, the credential data is reduced to 76 bytes compared to 140 bytes with GZIP, cutting storage and bandwidth costs. The system also supports fine-grained status updates and Layer-2 blockchain anchoring for tamper-evident, low-cost verification. The system employs reusable verifiable presentations (VPs) with unique access tokens, enabling cost-free verification and stronger access control. Selective disclosure preserves user control and strengthens privacy. Finally, the system integrates SHA3 hashing and Falcon post-quantum signatures. This guarantees robustness against quantum attacks, transparency, and scalability. It is a future-proof solution for national-scale identity verification, as demonstrated by experimental findings and security studies that validate its robustness and applicability.

cs.CR↗

arXiv2026

Reflex-Guard: A Low-Latency Guardrail for LLM Prompt Safety Using Dense Semantic Embeddings

Large Language Models (LLMs) in real-world applications often face the risks of specially crafted prompts designed to bypass the safety controls. Existing guardrail methods, such as LLM-as-a-judge and cloud-based safety APIs are able to detect unsafe content. However, they often add a delay of about 250-900 ms to each request. This delay is too high for real-time applications, when the system usually needs to respond in less than 100 ms. Furthermore, routing user prompts through external moderation endpoints raises significant data privacy concerns. This paper introduces Reflex-Guard, a lightweight guardrail that runs locally. It uses jailbreak-aware preprocessing, compact sentence-transformer embeddings, and seven fast binary classifiers. Together, these components enable high-accuracy prompt safety filtering with much lower latency than existing solutions. Through systematic evaluation on a strategically balanced dataset of 30,568 samples drawn from five complementary sources, we demonstrate that Reflex-Guard achieves 95.9% recall on harmful prompts at 37.6 ms end-to-end latency. It is faster than existing baselines, including Llama Guard 2 at 255 ms and SafeDecoding at 723 ms. It can detect 100% of GCG suffix attacks and Base64-encoded prompts using the default threshold. However, DrAttack structured prompts required lowering the threshold to 0.03 for optimal detection, as they produced a distinct probability distribution. Reflex-Guard achieves Reflex Efficiency Score (RES) scores up to 16.79, significantly outperforming Llama Guard 2 (11.90) and SafeDecoding (9.80). This analysis offers practical deployment advice and shows that different attack types occupy distinct regions in the embedding probability space.

cs.CR↗