SecureRouter is an encrypted routing and inference framework that accelerates secure transformer inference by adaptively selecting the optimal model size based on the encrypted input, achieving a 1.95…

This paper provides a comprehensive, system-level comparison of MPC and FHE for Privacy-Preserving Machine Learning (PPML) across various models and environments, moving beyond single-metric latency a…

RouteScan introduces a non-intrusive framework that audits the safety of Mixture-of-Experts (MoE) LLMs by analyzing low-level GPU expert routing telemetry, achieving high accuracy even on unseen harmf…

The paper systematically evaluates eight privacy-preserving techniques for LLM requests, finding that a combination of local inference, redaction, and semantic rephrasing provides the best overall pro…

SharedRequest introduces a model-agnostic framework that enhances LLM privacy and efficiency by batching and mixing prompts with noisy variants, achieving high utility and significant cost reduction.

The paper proposes RPSG, a method that uses private seeds and differential privacy to generate highly realistic and strongly privacy-preserving synthetic data replicas of private text for LLMs.

The paper introduces R$^2$A, an adversarial attack that uses suffix optimization to mislead black-box LLM routers into consistently selecting expensive, high-capability models.

CachePrune introduces a privacy-aware, fine-grained KV cache sharing mechanism that allows LLM inference systems to safely reuse cache entries across users' requests, significantly improving efficienc…

SS-ZKR is a novel, three-mechanism protocol that enables privacy-preserving, content-based semantic routing of agent payloads across organizational trust boundaries without requiring the intermediary…

SS-ZKR is a novel, three-mechanism protocol that enables privacy-preserving, content-based semantic routing of agent payloads across organizational trust boundaries without requiring the intermediary…

This survey provides a comprehensive, structured taxonomy of split learning techniques for fine-tuning Large Language Models (LLMs), covering model optimization, system efficiency, and privacy preserv…

The paper proposes an optimized, end-to-end privacy-preserving framework for vertical federated learning by distributing aggregation roles across multiple servers using secure multiparty computation a…

The paper proposes a novel framework combining evolutionary algorithms and Secure Multi-Party Computation (MPC) to enable privacy-preserving distributed optimization that meets strict time deadlines.

The paper proposes a novel identity-based public key management framework, IPK-pq, utilizing NIST ML-DSA and random matrix theory to enhance the scalability and efficiency of Public Key Infrastructure…

EncFormer is a novel two-party framework that significantly improves the efficiency and scalability of private Transformer inference by optimizing the combination of Fully Homomorphic Encryption (FHE)…

The paper introduces Privacy-Preserving Fine-Tuning (PPFT), a novel two-stage pipeline that allows LLMs to process sensitive data via pooled embeddings rather than raw text, achieving a strong balance…

Pepper is a novel, high-bandwidth anonymous broadcast protocol that achieves cryptographic sender anonymity and significantly improves messaging throughput compared to existing state-of-the-art system…

The paper introduces a 'Privacy Guard' framework that simultaneously reduces operational costs and eliminates data leakage risks when using LLMs by optimizing prompts and routing queries to secure mod…

This paper systematically analyzes the threat posed by malicious third-party API routers in the LLM supply chain, finding that a significant number of routers actively perform payload injection, crede…

The paper introduces ActInv and PAF to systematically analyze and quantify privacy leakage from intermediate activations during split inference of LLMs, proposing PriPert for enhanced defense.