paper-with-me

홈 › Papers

Private Transformer Inference in MLaaS: A Survey

2025-05-15 · Yang Li, Xinyu Zhou, Yitong Wang, Liangxin Qian, Jun Zhao

Transformer models have revolutionized AI, powering applications like content generation and sentiment analysis. However, their deployment in Machine Learning as a Service (MLaaS) raises significant privacy concerns, primarily due to the centralized processing of sensitive user data. Private Transformer Inference (PTI) offers a solution by utilizing cryptographic techniques such as secure multi-party computation and homomorphic encryption, enabling inference while preserving both user data and model privacy. This paper reviews recent PTI advancements, highlighting state-of-the-art solutions and challenges. We also introduce a structured taxonomy and evaluation framework for PTI, focusing on balancing resource efficiency with privacy and bridging the gap between high-performance inference and data privacy.

📄 PDF Abstract BibTeX arXiv:2505.10315

Code (0)

등록된 구현이 없습니다.

Tasks

Sentiment AnalysisSurvey

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

A Survey on Private Transformer Inference

2024-12-11 · Yang Li, Xinyu Zhou, Yitong Wang, Liangxin Qian 외

Transformer models have revolutionized AI, enabling applications like content generation and sentiment analysis. However, their use in Machine Learning as a Service (MLaaS) raises significant privacy concerns, as central…

Sentiment AnalysisSurvey

Feature Inference Attack on Shapley Values

2024-07-16 · Xinjian Luo, Yangfan Jiang, Xiaokui Xiao

As a solution concept in cooperative game theory, Shapley value is highly recognized in model interpretability studies and widely adopted by the leading Machine Learning as a Service (MLaaS) providers, such as Google, Mi…

Inference AttackPrivacy Preserving

PrivEdge: From Local to Distributed Private Training and Prediction

2020-04-12 · Ali Shahin Shamsabadi, Adria Gascon, Hamed Haddadi, Andrea Cavallaro

Machine Learning as a Service (MLaaS) operators provide model training and prediction on the cloud. MLaaS applications often rely on centralised collection and aggregation of user data, which could lead to significant pr…

Image CompressionPrivacy Preserving

Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions

2023-06-14 · Abdulrahman Diaa, Lucas Fenaux, Thomas Humphries, Marian Dietz 외

Machine Learning as a Service (MLaaS) is an increasingly popular design where a company with abundant computing resources trains a deep neural network and offers query access for tasks like image classification. The chal…

image-classificationImage Classification

Private Training Set Inspection in MLaaS

2023-05-15 · Mingxue Xu, Tongtong Xu, Po-Yu Chen

Machine Learning as a Service (MLaaS) is a popular cloud-based solution for customers who aim to use an ML model but lack training data, computation resources, or expertise in ML. In this case, the training datasets are …

DiversityFairnessMultiple Instance Learning