相关论文: Towards Anonymous Neural Network Inference

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…

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…