Image de couverture de livre

Cascade: Token-Sharded Private LLM Inference

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Thomas, Rahul, Zahran, Louai, Choi, Erica, Potti, Akilesh, Goldblum, Micah, Pal, Arka
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

An Attack to Break Permutation-Based Private Third-Party Inference Schemes for LLMs
par: Thomas, Rahul, et autres
Publié: (2025)

Privacy-Preserving Mechanisms Enable Cheap Verifiable Inference of LLMs
par: Pal, Arka, et autres
Publié: (2026)

vTune: Verifiable Fine-Tuning for LLMs Through Backdooring
par: Zhang, Eva, et autres
Publié: (2024)

Knowing What You Know Is Not Enough: Large Language Model Confidences Don't Align With Their Actions
par: Pal, Arka, et autres
Publié: (2025)

AERO: Entropy-Guided Framework for Private LLM Inference
par: Jha, Nandan Kumar, et autres
Publié: (2024)

TruncFormer: Private LLM Inference Using Only Truncations
par: Yubeaton, Patrick, et autres
Publié: (2024)

Cascading and Proxy Membership Inference Attacks
par: Du, Yuntao, et autres
Publié: (2025)

Adaptively Private Next-Token Prediction of Large Language Models
par: Flemings, James, et autres
Publié: (2024)

Noise-Aware Differentially Private Variational Inference
par: Alrawajfeh, Talal, et autres
Publié: (2024)

Dash: Accelerating Distributed Private Convolutional Neural Network Inference with Arithmetic Garbled Circuits
par: Sander, Jonas, et autres
Publié: (2023)

Differentially Private High-dimensional Variable Selection via Integer Programming
par: Prastakos, Petros, et autres
Publié: (2025)

CipherPrune: Efficient and Scalable Private Transformer Inference
par: Zhang, Yancheng, et autres
Publié: (2025)

Secure Aggregation is Not Private Against Membership Inference Attacks
par: Ngo, Khac-Hoang, et autres
Publié: (2024)

High-Resolution Convolutional Neural Networks on Homomorphically Encrypted Data via Sharding Ciphertexts
par: Maloney, Vivian, et autres
Publié: (2023)

Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions
par: Diaa, Abdulrahman, et autres
Publié: (2023)

Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption
par: Biswas, Sayan, et autres
Publié: (2025)

xMLP: Revolutionizing Private Inference with Exclusive Square Activation
par: Li, Jiajie, et autres
Publié: (2024)

RobPI: Robust Private Inference against Malicious Client
par: Xue, Jiaqi, et autres
Publié: (2026)

Improving the Utility of Differentially Private Clustering through Dynamical Processing
par: Byun, Junyoung, et autres
Publié: (2023)

Token-Efficient Change Detection in LLM APIs
par: Chauvin, Timothée, et autres
Publié: (2026)

Differentially Private Covariate Balancing Causal Inference
par: Ohnishi, Yuki, et autres
Publié: (2024)

Differentially Private Learned Indexes
par: Du, Jianzhang, et autres
Publié: (2024)

Dynamic Delayed Tree Expansion For Improved Multi-Path Speculative Decoding
par: Thomas, Rahul, et autres
Publié: (2026)

Scalable Federated Unlearning via Isolated and Coded Sharding
par: Lin, Yijing, et autres
Publié: (2024)

DeepShare: Sharing ReLU Across Channels and Layers for Efficient Private Inference
par: Bornfeld, Yonathan, et autres
Publié: (2025)

AdaPI: Facilitating DNN Model Adaptivity for Efficient Private Inference in Edge Computing
par: Zhou, Tong, et autres
Publié: (2024)

GNNBleed: Inference Attacks to Unveil Private Edges in Graphs with Realistic Access to GNN Models
par: Song, Zeyu, et autres
Publié: (2023)

NeuJeans: Private Neural Network Inference with Joint Optimization of Convolution and FHE Bootstrapping
par: Ju, Jae Hyung, et autres
Publié: (2023)

NoEsis: Differentially Private Knowledge Transfer in Modular LLM Adaptation
par: Romijnders, Rob, et autres
Publié: (2025)

Private Estimation when Data and Privacy Demands are Correlated
par: Chaudhuri, Syomantak, et autres
Publié: (2024)

On the Reliability of Watermarks for Large Language Models
par: Kirchenbauer, John, et autres
Publié: (2023)

Order of Magnitude Speedups for LLM Membership Inference
par: Zhang, Rongting, et autres
Publié: (2024)

Differentially Private Next-Token Prediction of Large Language Models
par: Flemings, James, et autres
Publié: (2024)

Verifying LLM Inference to Detect Model Weight Exfiltration
par: Rinberg, Roy, et autres
Publié: (2025)

PE-means: Improved Differentially Private $k$-means Clustering through Private Evolution
par: Humphries, Thomas, et autres
Publié: (2026)

Privately Learning Decision Lists and a Differentially Private Winnow
par: Bun, Mark, et autres
Publié: (2026)

Adversary-Aware Private Inference over Wireless Channels
par: Seif, Mohamed, et autres
Publié: (2025)

Linearizing Models for Efficient yet Robust Private Inference
par: Sarkar, Sreetama, et autres
Publié: (2024)

Disparate Impact on Group Accuracy of Linearization for Private Inference
par: Das, Saswat, et autres
Publié: (2024)

Differentially Private Datastore Generation for Retrieval-Augmented Inference
par: Abouelenein, Abdelrahman, et autres
Publié: (2026)