English
Related papers

Related papers: Towards Anonymous Neural Network Inference

200 papers

Anonymity networks hide user identities with the help of relayed anonymity routers. However, the state-of-the-art anonymity networks do not provide an effective trust model. As a result, users cannot circumvent malicious or vulnerable…

Cryptography and Security · Computer Science 2013-01-22 Peng Zhou , Xiapu Luo , Ang Chen , Rocky K. C. Chang

End-to-end encrypted (E2EE) messaging is an essential first step in providing message confidentiality. Unfortunately, all security guarantees of end-to-end encryption are lost when keys or plaintext are disclosed, either due to device…

Cryptography and Security · Computer Science 2023-06-13 Anrin Chakraborti , Darius Suciu , Radu Sion

In the era of big data, anonymity is recognized as an important attribute in privacy-preserving communications. The existing anonymous authentication and routing are applied at higher layers of networks, ignoring physical layer (PHY) also…

Information Theory · Computer Science 2020-10-20 Zhongxiang Wei , Fan Liu , Christos Masouros , H. Vincent Poor

Increasing awareness of privacy-preserving has led to a strong focus on anonymous systems protecting anonymity. By studying early schemes, we summarize some intractable problems of anonymous systems. Centralization setting is a universal…

Cryptography and Security · Computer Science 2020-09-25 Renpeng Zou , Xixiang Lv

The rapid expansion of Artificial Intelligence is hindered by a fundamental friction in data markets: the value-privacy dilemma, where buyers cannot verify a dataset's utility without inspection, yet inspection may expose the data (Arrow's…

Cryptography and Security · Computer Science 2026-03-25 Michael Yang , Ruijiang Gao , Zhiqiang Zheng

The increasing capabilities of deep neural networks for re-identification, combined with the rise in public surveillance in recent years, pose a substantial threat to individual privacy. Event cameras were initially considered as a…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Katharina Bendig , René Schuster , Nicole Thiemer , Karen Joisten , Didier Stricker

Protecting the privacy of input data is of growing importance as machine learning methods reach new application domains. In this paper, we provide a unified training and inference framework for large DNNs while protecting input privacy and…

Cryptography and Security · Computer Science 2020-10-19 Hanieh Hashemi , Yongqin Wang , Murali Annavaram

As intelligent sensing expands into high-privacy environments such as restrooms and changing rooms, the field faces a critical privacy-security paradox. Traditional RGB surveillance raises significant concerns regarding visual recording and…

Cryptography and Security · Computer Science 2026-02-02 Huan Song , Shuyu Tian , Junyi Hao , Cheng Yuan , Zhenyu Jia , Jiawei Shao , Xuelong Li

Computational privacy is a property of cryptographic system that ensures the privacy of data being processed at an untrusted server. Fully Homomorphic Encryption Schemes (FHE) promise to provide such property. Contemporary FHE schemes are…

Cryptography and Security · Computer Science 2014-06-10 Sashank Dara

The escalating focus on data privacy poses significant challenges for collaborative neural network training, where data ownership and model training/deployment responsibilities reside with distinct entities. Our community has made…

Cryptography and Security · Computer Science 2024-03-19 Xuanqi Liu , Zhuotao Liu , Qi Li , Ke Xu , Mingwei Xu

We introduce the notion of \emph{traceable mixnets}. In a traditional mixnet, multiple mix-servers jointly permute and decrypt a list of ciphertexts to produce a list of plaintexts, along with a proof of correctness, such that the…

Cryptography and Security · Computer Science 2024-06-25 Prashant Agrawal , Abhinav Nakarmi , Mahavir Prasad Jhawar , Subodh Sharma , Subhashis Banerjee

Finger vein recognition technology has become one of the primary solutions for high-security identification systems. However, it still has information leakage problems, which seriously jeopardizes users privacy and anonymity and cause great…

Computer Vision and Pattern Recognition · Computer Science 2024-09-24 Yifan Wang , Jie Gui , Yuan Yan Tang , James Tin-Yau Kwok

In this paper we consider the variable-length lossless source coding for discrete memoryless sources. We proposes a new encryption framework for securely transmitting codewords over a noiseless channel. The proposed source encryption…

Information Theory · Computer Science 2026-05-26 Yasutada Oohama , Bagus Santoso

We introduce a new class of non-linear function-on-function regression models for functional data using neural networks. We propose a framework using a hidden layer consisting of continuous neurons, called a continuous hidden layer, for…

Methodology · Statistics 2023-10-10 Aniruddha Rajendra Rao , Matthew Reimherr

Mixnets provide strong meta-data privacy and recent academic research and industrial projects have made strides in making them more secure, performance, and scalable. In this paper, we focus our work on stratified Mixnets -- a popular…

Cryptography and Security · Computer Science 2022-08-05 Xinshu Ma , Florentin Rochet , Tariq Elahi

Advanced computer vision technology can provide near real-time home monitoring to support "aging in place" by detecting falls and symptoms related to seizures and stroke. Affordable webcams, together with cloud computing services (to run…

Cryptography and Security · Computer Science 2022-08-10 Miran Kim , Xiaoqian Jiang , Kristin Lauter , Elkhan Ismayilzada , Shayan Shams

Ensuring privacy during inference stage is crucial to prevent malicious third parties from reconstructing users' private inputs from outputs of public models. Despite a large body of literature on privacy preserving learning (which ensures…

Cryptography and Security · Computer Science 2024-12-02 Fengwei Tian , Ravi Tandon

We present RHODE, a novel system that enables privacy-preserving training of and prediction on Recurrent Neural Networks (RNNs) in a cross-silo federated learning setting by relying on multiparty homomorphic encryption. RHODE preserves the…

Cryptography and Security · Computer Science 2023-05-04 Sinem Sav , Abdulrahman Diaa , Apostolos Pyrgelis , Jean-Philippe Bossuat , Jean-Pierre Hubaux

We study the problem of providing privacy-preserving access to an outsourced honest-but-curious data repository for a group of trusted users. We show that such privacy-preserving data access is possible using a combination of probabilistic…

Cryptography and Security · Computer Science 2011-05-23 Michael T. Goodrich , Michael Mitzenmacher , Olga Ohrimenko , Roberto Tamassia

Federated learning has become increasingly widespread due to its ability to train models collaboratively without centralizing sensitive data. While most research on FL emphasizes privacy-preserving techniques during training, the evaluation…

Cryptography and Security · Computer Science 2025-08-12 Cem Ata Baykara , Ali Burak Ünal , Mete Akgün