Search Results for author: Yuan Hong

Found 15 papers, 2 papers with code

Differentially Private Instance Encoding against Privacy Attacks

no code implementations NAACL (ACL) 2022 Shangyu Xie, Yuan Hong

TextHide was recently proposed to protect the training data via instance encoding in natural language domain.

Reconstruction Attack

Reconstruction Attack on Instance Encoding for Language Understanding

no code implementations EMNLP 2021 Shangyu Xie, Yuan Hong

A private learning scheme TextHide was recently proposed to protect the private text data during the training phase via so-called instance encoding.

Privacy Preserving Reconstruction Attack +1

Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks

no code implementations31 Jul 2023 Xinyu Zhang, Hanbin Hong, Yuan Hong, Peng Huang, Binghui Wang, Zhongjie Ba, Kui Ren

The language models, especially the basic text classification models, have been shown to be susceptible to textual adversarial attacks such as synonym substitution and word insertion attacks.

text-classification Text Classification

Certifiable Black-Box Attack: Ensuring Provably Successful Attack for Adversarial Examples

no code implementations10 Apr 2023 Hanbin Hong, Yuan Hong

To craft the adversarial examples with the certifiable attack success rate (CASR) guarantee, we design several novel techniques, including a randomized query method to query the target model, an initialization method with smoothed self-supervised perturbation to derive certifiable adversarial examples, and a geometric shifting method to reduce the perturbation size of the certifiable adversarial examples for better imperceptibility.

OpBoost: A Vertical Federated Tree Boosting Framework Based on Order-Preserving Desensitization

1 code implementation4 Oct 2022 Xiaochen Li, Yuke Hu, Weiran Liu, Hanwen Feng, Li Peng, Yuan Hong, Kui Ren, Zhan Qin

Although the solution based on Local Differential Privacy (LDP) addresses the above problems, it leads to the low accuracy of the trained model.

Federated Learning Privacy Preserving

UniCR: Universally Approximated Certified Robustness via Randomized Smoothing

no code implementations5 Jul 2022 Hanbin Hong, Binghui Wang, Yuan Hong

We study certified robustness of machine learning classifiers against adversarial perturbations.

DPOAD: Differentially Private Outsourcing of Anomaly Detection through Iterative Sensitivity Learning

no code implementations27 Jun 2022 Meisam Mohammady, Han Wang, Lingyu Wang, Mengyuan Zhang, Yosr Jarraya, Suryadipta Majumdar, Makan Pourzandi, Mourad Debbabi, Yuan Hong

Outsourcing anomaly detection to third-parties can allow data owners to overcome resource constraints (e. g., in lightweight IoT devices), facilitate collaborative analysis (e. g., under distributed or multi-party scenarios), and benefit from lower costs and specialized expertise (e. g., of Managed Security Service Providers).

Anomaly Detection

Infrastructure-enabled GPS Spoofing Detection and Correction

no code implementations11 Feb 2022 Feilong Wang, Yuan Hong, Jeff Ban

Accurate and robust localization is crucial for supporting high-level driving automation and safety.

Autonomous Driving

An Eye for an Eye: Defending against Gradient-based Attacks with Gradients

no code implementations2 Feb 2022 Hanbin Hong, Yuan Hong, Yu Kong

In this paper, we show that the gradients can also be exploited as a powerful weapon to defend against adversarial attacks.

VideoDP: A Universal Platform for Video Analytics with Differential Privacy

no code implementations18 Sep 2019 Han Wang, Shangyu Xie, Yuan Hong

In this paper, to the best of our knowledge, we propose the first differentially private video analytics platform (VideoDP) which flexibly supports different video analyses with rigorous privacy guarantee.

Cannot find the paper you are looking for? You can Submit a new open access paper.