4.6 Article

Optimizing Privacy-Preserving Outsourced Convolutional Neural Network Predictions

Related references

Note: Only part of the references are listed.
Article Computer Science, Hardware & Architecture

Shielding Collaborative Learning: Mitigating Poisoning Attacks Through Client-Side Detection

Lingchen Zhao et al.

Summary: The article presents a novel defense scheme to detect anomalous updates in both IID and non-IID settings, while protecting client-level privacy to prevent poisoning attacks. Experimental evaluations show that the scheme is significantly robust against representative attacks.

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING (2021)

Article Computer Science, Hardware & Architecture

Blindfolded Evaluation of Random Forests with Multi-Key Homomorphic Encryption

Asma Aloufi et al.

Summary: The paper introduces a secure protocol for collaborative evaluation of random forests contributed by multiple owners, outsourced to a third-party evaluator. The cloud evaluates obliviously on individually encrypted random forest models and calculates the aggregated result, based on a new secure comparison protocol, secure counting protocol, and multi-key somewhat homomorphic encryption to reduce communication overheads and round complexity.

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING (2021)

Article Computer Science, Hardware & Architecture

Invisible Adversarial Attack against Deep Neural Networks: An Adaptive Penalization Approach

Zhibo Wang et al.

Summary: Recent studies have shown that deep neural networks are vulnerable to adversarial examples, which poses a threat to security-sensitive applications. Existing methods for synthesizing adversarial examples have limitations, leading to noticeable artifacts in certain regions. This paper introduces an invisible adversarial attack that generates visually indistinguishable adversarial examples by adaptively distributing perturbations based on human sensitivity. Experimental results demonstrate the effectiveness of the proposed method in generating indistinguishable adversarial examples.

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING (2021)

Article Engineering, Electrical & Electronic

Robust Lane Detection From Continuous Driving Scenes Using Deep Neural Networks

Qin Zou et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2020)

Article Computer Science, Theory & Methods

Privacy-Preserving Collaborative Deep Learning With Unreliable Participants

Lingchen Zhao et al.

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY (2020)

Article Computer Science, Theory & Methods

Deep Learning-Based Gait Recognition Using Smartphones in the Wild

Qin Zou et al.

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY (2020)

Article Computer Science, Artificial Intelligence

Privacy-Preserving Collaborative Model Learning: The Case of Word Vector Training

Qian Wang et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2018)

Article Engineering, Electrical & Electronic

Manual for Using Homomorphic Encryption for Bioinformatics

Nathan Dowlin et al.

PROCEEDINGS OF THE IEEE (2017)

Proceedings Paper Computer Science, Information Systems

Oblivious Neural Network Predictions via MiniONN Transformations

Jian Liu et al.

CCS'17: PROCEEDINGS OF THE 2017 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY (2017)

Proceedings Paper Computer Science, Information Systems

ABY - A Framework for Efficient Mixed-Protocol Secure Two-Party Computation

Daniel Demmler et al.

22ND ANNUAL NETWORK AND DISTRIBUTED SYSTEM SECURITY SYMPOSIUM (NDSS 2015) (2015)

Proceedings Paper Computer Science, Information Systems

Machine Learning Classification over Encrypted Data

Raphael Bost et al.

22ND ANNUAL NETWORK AND DISTRIBUTED SYSTEM SECURITY SYMPOSIUM (NDSS 2015) (2015)

Article Computer Science, Theory & Methods

Fully homomorphic SIMD operations

N. P. Smart et al.

DESIGNS CODES AND CRYPTOGRAPHY (2014)