Search Results for author: Huiying Li

Found 11 papers, 6 papers with code

On the Permanence of Backdoors in Evolving Models

no code implementations8 Jun 2022 Huiying Li, Arjun Nitin Bhagoji, Yuxin Chen, Haitao Zheng, Ben Y. Zhao

Existing research on training-time attacks for deep neural networks (DNNs), such as backdoors, largely assume that models are static once trained, and hidden backdoors trained into models remain active indefinitely.

Leveraging Table Content for Zero-shot Text-to-SQL with Meta-Learning

1 code implementation12 Sep 2021 Yongrui Chen, Xinnan Guo, Chaojie Wang, Jian Qiu, Guilin Qi, Meng Wang, Huiying Li

Compared to the larger pre-trained model and the tabular-specific pre-trained model, our approach is still competitive.

Meta-Learning Text-To-SQL

Formal Query Building with Query Structure Prediction for Complex Question Answering over Knowledge Base

1 code implementation8 Sep 2021 Yongrui Chen, Huiying Li, Yuncheng Hua, Guilin Qi

However, this candidate generation strategy ignores the structure of queries, resulting in a considerable number of noisy queries.

Graph Generation Question Answering

Blacklight: Scalable Defense for Neural Networks against Query-Based Black-Box Attacks

1 code implementation24 Jun 2020 Huiying Li, Shawn Shan, Emily Wenger, Jiayun Zhang, Hai-Tao Zheng, Ben Y. Zhao

In particular, query-based black-box attacks do not require knowledge of the deep learning model, but can compute adversarial examples over the network by submitting queries and inspecting returns.

Image Classification text-classification +1

Fawkes: Protecting Privacy against Unauthorized Deep Learning Models

1 code implementation19 Feb 2020 Shawn Shan, Emily Wenger, Jiayun Zhang, Huiying Li, Hai-Tao Zheng, Ben Y. Zhao

In this paper, we propose Fawkes, a system that helps individuals inoculate their images against unauthorized facial recognition models.

Face Recognition Privacy Preserving Deep Learning

Piracy Resistant Watermarks for Deep Neural Networks

1 code implementation2 Oct 2019 Huiying Li, Emily Wenger, Shawn Shan, Ben Y. Zhao, Haitao Zheng

We empirically show that our proposed watermarks achieve piracy resistance and other watermark properties, over a wide range of tasks and models.

Transfer Learning

Regula Sub-rosa: Latent Backdoor Attacks on Deep Neural Networks

no code implementations24 May 2019 Yuanshun Yao, Huiying Li, Hai-Tao Zheng, Ben Y. Zhao

Recent work has proposed the concept of backdoor attacks on deep neural networks (DNNs), where misbehaviors are hidden inside "normal" models, only to be triggered by very specific inputs.

Backdoor Attack Traffic Sign Recognition +1

Sparse representation-based over-sampling technique for classification of imbalanced dataset

no code implementations journal 2017 Xionggao Zou, Yueping Feng, Huiying Li, Shuyu Jiang

As one of the most popular research fields in machine learning, the research on imbalanced dataset receives more and more attentions in recent years.

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