Cascade: Token-Sharded Private LLM Inference

• URL: http://arxiv.org/abs/2507.05228v1
• Date: Mon, 07 Jul 2025 17:37:16 GMT
• Title: Cascade: Token-Sharded Private LLM Inference
• Authors: Rahul Thomas, Louai Zahran, Erica Choi, Akilesh Potti, Micah Goldblum, Arka Pal,
• Abstract summary: We propose a new multi-party inference protocol, Cascade, that avoids punitive costs by leveraging sharding in the sequence dimension to maintain privacy.<n>We demonstrate that Cascade is resistant to a generalization of a recent attack that is highly effective against other statistical privacy schemes.
• Score: 31.561665382764076
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: As LLMs continue to increase in parameter size, the computational resources required to run them are available to fewer parties. Therefore, third-party inference services -- where LLMs are hosted by third parties with significant computational resources -- are becoming increasingly popular. However, third party inference raises critical concerns about user data privacy. To mitigate these risks, privacy researchers have developed provably secure schemes for third-party inference, such as Secure Multi-Party Computation (SMPC). However, SMPC protocols have significant computational and communication overhead, and do not scale to large models. In this work, we propose a new multi-party inference protocol, Cascade, that avoids these punitive costs by leveraging sharding in the sequence dimension to maintain privacy, trading off cryptographic privacy guarantees for increased performance and scalability. We demonstrate that Cascade is resistant to a generalization of a recent attack that is highly effective against other statistical privacy schemes, and that it is further resistant to learning-based attacks. As Cascade is orders of magnitude faster than existing schemes, our findings offer practical solutions for secure deployment of modern state-of-the-art LLMs.

Related papers

• Federated Learning-Enabled Hybrid Language Models for Communication-Efficient Token Transmission [87.68447072141402]
  Hybrid Language Models (HLMs) combine the low-latency efficiency of Small Language Models (SLMs) on edge devices with the high accuracy of Large Language Models (LLMs) on centralized servers.<n>We propose FedHLM, a communication-efficient HLM framework that integrates uncertainty-aware inference with Federated Learning (FL)
  arXiv  Detail & Related papers  (2025-06-30T02:56:11Z)
• FedShield-LLM: A Secure and Scalable Federated Fine-Tuned Large Language Model [0.48342038441006796]
  Federated Learning (FL) offers a decentralized framework for training and fine-tuning Large Language Models (LLMs)<n>FL addresses privacy and security concerns while navigating challenges associated with the substantial computational demands of LLMs.<n>We propose a novel method, FedShield-LLM, that uses pruning with Fully Homomorphic Encryption (FHE) for Low-Rank Adaptation (LoRA) parameters.
  arXiv  Detail & Related papers  (2025-06-06T00:05:05Z)
• An Attack to Break Permutation-Based Private Third-Party Inference Schemes for LLMs [31.561665382764076]
  Recent advances in Large Language Models (LLMs) have led to the widespread adoption of third-party inference services.<n>Existing methods of performing private third-party inference, such as Secure Multiparty Computation (SMPC), often rely on cryptographic methods.<n>We introduce a novel reconstruction technique that can recover original prompts from hidden states with nearly perfect accuracy.
  arXiv  Detail & Related papers  (2025-05-23T19:39:18Z)
• PWC-MoE: Privacy-Aware Wireless Collaborative Mixture of Experts [59.5243730853157]
  Large language models (LLMs) hosted on cloud servers alleviate the computational and storage burdens on local devices but raise privacy concerns.<n>Small language models (SLMs) running locally enhance privacy but suffer from limited performance on complex tasks.<n>We propose a privacy-aware wireless collaborative mixture of experts (PWC-MoE) framework to balance computational cost, performance, and privacy protection under bandwidth constraints.
  arXiv  Detail & Related papers  (2025-05-13T16:27:07Z)
• Efficient Full-Stack Private Federated Deep Learning with Post-Quantum Security [17.45950557331482]
  Federated learning (FL) enables collaborative model training while preserving user data privacy by keeping data local.<n>Despite these advantages, FL remains vulnerable to privacy attacks on user updates and model parameters during training and deployment.<n>We introduce Beskar, a novel framework that provides post-quantum secure aggregation.
  arXiv  Detail & Related papers  (2025-05-09T03:20:48Z)
• Enhancing Feature-Specific Data Protection via Bayesian Coordinate Differential Privacy [55.357715095623554]
  Local Differential Privacy (LDP) offers strong privacy guarantees without requiring users to trust external parties. We propose a Bayesian framework, Bayesian Coordinate Differential Privacy (BCDP), that enables feature-specific privacy quantification.
  arXiv  Detail & Related papers  (2024-10-24T03:39:55Z)
• PriRoAgg: Achieving Robust Model Aggregation with Minimum Privacy Leakage for Federated Learning [49.916365792036636]
  Federated learning (FL) has recently gained significant momentum due to its potential to leverage large-scale distributed user data.<n>The transmitted model updates can potentially leak sensitive user information, and the lack of central control of the local training process leaves the global model susceptible to malicious manipulations on model updates.<n>We develop a general framework PriRoAgg, utilizing Lagrange coded computing and distributed zero-knowledge proof, to execute a wide range of robust aggregation algorithms while satisfying aggregated privacy.
  arXiv  Detail & Related papers  (2024-07-12T03:18:08Z)
• SSNet: A Lightweight Multi-Party Computation Scheme for Practical Privacy-Preserving Machine Learning Service in the Cloud [17.961150835215587]
  We propose SSNet, which for the first time employs Shamir's secret sharing (SSS) as the backbone of MPC-based ML framework. SSNet demonstrates the ability to scale up party numbers straightforwardly and embeds strategies to authenticate the computation correctness. We conduct comprehensive experimental evaluations on commercial cloud computing infrastructure from Amazon AWS.
  arXiv  Detail & Related papers  (2024-06-04T00:55:06Z)
• Privacy-Preserving Distributed Learning for Residential Short-Term Load Forecasting [11.185176107646956]
  Power system load data can inadvertently reveal the daily routines of residential users, posing a risk to their property security. We introduce a Markovian Switching-based distributed training framework, the convergence of which is substantiated through rigorous theoretical analysis. Case studies employing real-world power system load data validate the efficacy of our proposed algorithm.
  arXiv  Detail & Related papers  (2024-02-02T16:39:08Z)
• Is Vertical Logistic Regression Privacy-Preserving? A Comprehensive Privacy Analysis and Beyond [57.10914865054868]
  We consider vertical logistic regression (VLR) trained with mini-batch descent gradient. We provide a comprehensive and rigorous privacy analysis of VLR in a class of open-source Federated Learning frameworks.
  arXiv  Detail & Related papers  (2022-07-19T05:47:30Z)
• Distributed Reinforcement Learning for Privacy-Preserving Dynamic Edge Caching [91.50631418179331]
  A privacy-preserving distributed deep policy gradient (P2D3PG) is proposed to maximize the cache hit rates of devices in the MEC networks. We convert the distributed optimizations into model-free Markov decision process problems and then introduce a privacy-preserving federated learning method for popularity prediction.
  arXiv  Detail & Related papers  (2021-10-20T02:48:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.