28 citations · 48 across the 11 of their papers we have counts for
11 papers
Universal Defensive Underpainting Patch: Making Your Text Invisible to Optical Character Recognition
JiaCheng Deng, Li Dong, Jiahao Chen +5
Optical Character Recognition (OCR) enables automatic text extraction from scanned or digitized text images, but it also makes it easy to pirate valuable or sensitive text from the…
Breaking Speaker Recognition with PaddingBack
Zhe Ye, Diqun Yan, Li Dong +1
Machine Learning as a Service (MLaaS) has gained popularity due to advancements in Deep Neural Networks (DNNs). However, untrusted third-party platforms have raised concerns about…
Fake the Real: Backdoor Attack on Deep Speech Classification via Voice Conversion
Zhe Ye, Terui Mao, Li Dong +1
Deep speech classification has achieved tremendous success and greatly promoted the emergence of many real-world applications. However, backdoor attacks present a new security thre…
Semi-Supervised Semantic Segmentation with Cross Teacher Training
Hui Xiao, Li Dong, Kangkang Song +4
Convolutional neural networks can achieve remarkable performance in semantic segmentation tasks. However, such neural network approaches heavily rely on costly pixel-level annotati…
Adversarial Privacy Protection on Speech Enhancement
Mingyu Dong, Diqun Yan, Rangding Wang
Speech is easily leaked imperceptibly, such as being recorded by mobile phones in different situations. Private content in speech may be maliciously extracted through speech enhanc…
Detecting and Recovering Adversarial Examples from Extracting Non-robust and Highly Predictive Adversarial Perturbations
Mingyu Dong, Jiahao Chen, Diqun Yan +3
Deep neural networks (DNNs) have been shown to be vulnerable against adversarial examples (AEs) which are maliciously designed to fool target models. The normal examples (NEs) adde…
Transferability of Adversarial Attacks on Synthetic Speech Detection
Jiacheng Deng, Shunyi Chen, Li Dong +2
Synthetic speech detection is one of the most important research problems in audio security. Meanwhile, deep neural networks are vulnerable to adversarial attacks. Therefore, we es…
Residual-Guided Non-Intrusive Speech Quality Assessment
Zhe Ye, Jiahao Chen, Diqun Yan
This paper proposes an approach to improve Non-Intrusive speech quality assessment(NI-SQA) based on the residuals between impaired speech and enhanced speech. The difficulty in our…
Adversarial Attacks on Machinery Fault Diagnosis
Jiahao Chen, Diqun Yan
Despite the great progress of neural network-based (NN-based) machinery fault diagnosis methods, their robustness has been largely neglected, for they can be easily fooled through…
Adversarial Example Devastation and Detection on Speech Recognition System by Adding Random Noise
Mingyu Dong, Diqun Yan, Yongkang Gong +1
An automatic speech recognition (ASR) system based on a deep neural network is vulnerable to attack by an adversarial example, especially if the command-dependent ASR fails. A defe…
Identification of fake stereo audio
Tianyun Liu, Diqun Yan
Channel is one of the important criterions for digital audio quality. General-ly, stereo audio two channels can provide better perceptual quality than mono audio. To seek illegal c…