English
Related papers

Related papers: Partially Oblivious Neural Network Inference

200 papers

Machine Learning (ML) models have been shown to potentially leak sensitive information, thus raising privacy concerns in ML-driven applications. This inspired recent research on removing the influence of specific data samples from a trained…

Machine Learning · Computer Science 2023-10-30 Youyang Qu , Xin Yuan , Ming Ding , Wei Ni , Thierry Rakotoarivelo , David Smith

Model compression has emerged as an important area of research for deploying deep learning models on Internet-of-Things (IoT). However, for extremely memory-constrained scenarios, even the compressed models cannot fit within the memory of a…

Machine Learning · Statistics 2019-07-30 Kartikeya Bhardwaj , Chingyi Lin , Anderson Sartor , Radu Marculescu

In cross-device federated learning (FL) setting, clients such as mobiles cooperate with the server to train a global machine learning model, while maintaining their data locally. However, recent work shows that client's private information…

Machine Learning · Computer Science 2021-11-02 Oualid Zari , Chuan Xu , Giovanni Neglia

In contemporary cloud-based services, protecting users' sensitive data and ensuring the confidentiality of the server's model are critical. Fully homomorphic encryption (FHE) enables inference directly on encrypted inputs, but its…

A large body of work shows that machine learning (ML) models can leak sensitive or confidential information about their training data. Recently, leakage due to distribution inference (or property inference) attacks is gaining attention. In…

Cryptography and Security · Computer Science 2022-09-20 Valentin Hartmann , Léo Meynent , Maxime Peyrard , Dimitrios Dimitriadis , Shruti Tople , Robert West

Large Language Models (LLMs) are increasingly served on shared accelerators where an adversary with read access to device memory can observe KV caches and hidden states, threatening prompt privacy for open-source models. Cryptographic…

Cryptography and Security · Computer Science 2026-03-09 Anatoly Belikov , Ilya Fedotov

We present a framework for fully-simulatable $h$-out-of-$n$ oblivious transfer ($OT^{n}_{h}$) with security against non-adaptive malicious adversaries. The framework costs six communication rounds and costs at most $40n$ public-key…

Cryptography and Security · Computer Science 2011-04-04 Bing Zeng , Xueming Tang , Chingfang Hsu

With the wide adoption of AI applications, there is a pressing need of enabling real-time neural network (NN) inference on small embedded devices, but deploying NNs and achieving high performance of NN inference on these small devices is…

Machine Learning · Computer Science 2023-12-25 Kai Huang , Wei Gao

Machine learning (ML) explainability is central to algorithmic transparency in high-stakes settings such as predictive diagnostics and loan approval. However, these same domains require rigorous privacy guaranties, creating tension between…

Cryptography and Security · Computer Science 2026-01-08 Firas Ben Hmida , Zain Sbeih , Philemon Hailemariam , Birhanu Eshete

Deep neural networks (DNNs) have become powerful tools for modeling complex data structures through sequentially integrating simple functions in each hidden layer. In survival analysis, recent advances of DNNs primarily focus on enhancing…

Machine Learning · Statistics 2025-03-26 Changhui Yuan , Shishun Zhao , Shuwei Li , Xinyuan Song , Zhao Chen

The ability to remove features from the input of machine learning models is very important to understand and interpret model predictions. However, this is non-trivial for vision models since masking out parts of the input image typically…

Computer Vision and Pattern Recognition · Computer Science 2023-10-31 Sriram Balasubramanian , Soheil Feizi

Confidential multi-stakeholder machine learning (ML) allows multiple parties to perform collaborative data analytics while not revealing their intellectual property, such as ML source code, model, or datasets. State-of-the-art solutions…

Machine Learning · Computer Science 2021-06-04 Wojciech Ozga , Do Le Quoc , Christof Fetzer

Aiming to reduce the cost and complexity of maintaining networking infrastructures, organizations are increasingly outsourcing their network functions (e.g., firewalls, traffic shapers and intrusion detection systems) to the cloud, and a…

Cryptography and Security · Computer Science 2016-01-26 Luca Melis , Hassan Jameel Asghar , Emiliano De Cristofaro , Mohamed Ali Kaafar

Intent obfuscation is a common tactic in adversarial situations, enabling the attacker to both manipulate the target system and avoid culpability. Surprisingly, it has rarely been implemented in adversarial attacks on machine learning…

Cryptography and Security · Computer Science 2024-08-30 Zhaobin Li , Patrick Shafto

Previous studies have found that an adversary attacker can often infer unintended input information from intermediate-layer features. We study the possibility of preventing such adversarial inference, yet without too much accuracy…

Machine Learning · Computer Science 2020-01-15 Liyao Xiang , Haotian Ma , Hao Zhang , Yifan Zhang , Jie Ren , Quanshi Zhang

Most existing secure neural network inference protocols based on secure multi-party computation (MPC) typically support at most four participants, demonstrating severely limited scalability. Liu et al. (USENIX Security'24) presented the…

Cryptography and Security · Computer Science 2026-04-23 Qinghui Zhang , Xiaojun Chen , Yansong Zhang , Xudong Chen

Privacy protection has become an increasing concern in modern machine learning applications. Privacy-preserving machine learning (PPML) has attracted growing research attention, with approaches such as secure multiparty computation (MPC)…

Cryptography and Security · Computer Science 2026-04-22 Pengzhi Huang , Kiwan Maeng , G. Edward Suh

This paper investigates the piracy problem of deep learning models. Designing and training a well-performing model is generally expensive. However, when releasing them, attackers may reverse engineer the models and pirate their design. This…

Cryptography and Security · Computer Science 2018-06-28 Hui Xu , Yuxin Su , Zirui Zhao , Yangfan Zhou , Michael R. Lyu , Irwin King

Many inference services based on large language models (LLMs) pose a privacy concern, either revealing user prompts to the service or the proprietary weights to the user. Secure inference offers a solution to this problem through secure…

Cryptography and Security · Computer Science 2024-08-08 Deevashwer Rathee , Dacheng Li , Ion Stoica , Hao Zhang , Raluca Popa

The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…

Machine Learning · Computer Science 2025-11-14 James Jin Kang , Dang Bui , Thanh Pham , Huo-Chong Ling