中文
相关论文

相关论文: VSVC: Backdoor attack against Keyword Spotting bas…

200 篇论文

Keyword spotting (KWS) has been widely used in various speech control scenarios. The training of KWS is usually based on deep neural networks and requires a large amount of data. Manufacturers often use third-party data to train KWS.…

声音 · 计算机科学 2022-11-17 Hanbo Cai , Pengcheng Zhang , Hai Dong , Yan Xiao , Shunhui Ji

Keyword spotting (KWS) is a critical component for enabling speech based user interactions on smart devices. It requires real-time response and high accuracy for good user experience. Recently, neural networks have become an attractive…

声音 · 计算机科学 2018-02-16 Yundong Zhang , Naveen Suda , Liangzhen Lai , Vikas Chandra

Recent studies revealed that deep neural networks (DNNs) are exposed to backdoor threats when training with third-party resources (such as training samples or backbones). The backdoored model has promising performance in predicting benign…

计算机视觉与模式识别 · 计算机科学 2023-03-07 Chengxiao Luo , Yiming Li , Yong Jiang , Shu-Tao Xia

Deep neural networks (DNNs) can be manipulated to exhibit specific behaviors when exposed to specific trigger patterns, without affecting their performance on benign samples, dubbed \textit{backdoor attack}. Currently, implementing backdoor…

计算机视觉与模式识别 · 计算机科学 2024-06-25 Ruotong Wang , Hongrui Chen , Zihao Zhu , Li Liu , Baoyuan Wu

Keyword spotting (KWS) refers to the task of identifying a set of predefined words in audio streams. With the advances seen recently with deep neural networks, it has become a popular technology to activate and control small devices, such…

音频与语音处理 · 电气工程与系统科学 2023-09-25 Heitor R. Guimarães , Arthur Pimentel , Anderson Avila , Tiago H. Falk

Voice Recognition Systems (VRSs) employ deep learning for speech recognition and speaker recognition. They have been widely deployed in various real-world applications, from intelligent voice assistance to telephony surveillance and…

密码学与安全 · 计算机科学 2023-07-26 Baochen Yan , Jiahe Lan , Zheng Yan

Deep neural networks (DNNs) have been widely and successfully adopted and deployed in various applications of speech recognition. Recently, a few works revealed that these models are vulnerable to backdoor attacks, where the adversaries can…

声音 · 计算机科学 2023-07-18 Hanbo Cai , Pengcheng Zhang , Hai Dong , Yan Xiao , Stefanos Koffas , Yiming Li

A keyword spotting (KWS) engine that is continuously running on device is exposed to various speech signals that are usually unseen before. It is a challenging problem to build a small-footprint and high-performing KWS model with robustness…

声音 · 计算机科学 2024-08-27 Zhenyu Wang , Li Wan , Biqiao Zhang , Yiteng Huang , Shang-Wen Li , Ming Sun , Xin Lei , Zhaojun Yang

Deep neural networks (DNNs) are vulnerable to a class of attacks called "backdoor attacks", which create an association between a backdoor trigger and a target label the attacker is interested in exploiting. A backdoored DNN performs well…

计算机视觉与模式识别 · 计算机科学 2023-01-23 Hasan Abed Al Kader Hammoud , Shuming Liu , Mohammed Alkhrashi , Fahad AlBalawi , Bernard Ghanem

Backdoor attack is a major threat to deep learning systems in safety-critical scenarios, which aims to trigger misbehavior of neural network models under attacker-controlled conditions. However, most backdoor attacks have to modify the…

机器学习 · 计算机科学 2023-08-24 Yizhen Yuan , Rui Kong , Shenghao Xie , Yuanchun Li , Yunxin Liu

Deep neural networks (DNN) have shown great success in many computer vision applications. However, they are also known to be susceptible to backdoor attacks. When conducting backdoor attacks, most of the existing approaches assume that the…

密码学与安全 · 计算机科学 2020-09-16 Haoliang Li , Yufei Wang , Xiaofei Xie , Yang Liu , Shiqi Wang , Renjie Wan , Lap-Pui Chau , Alex C. Kot

Deep neural networks (DNNs) have progressed rapidly during the past decade and have been deployed in various real-world applications. Meanwhile, DNN models have been shown to be vulnerable to security and privacy attacks. One such attack…

密码学与安全 · 计算机科学 2021-10-06 Xiaoyi Chen , Ahmed Salem , Dingfan Chen , Michael Backes , Shiqing Ma , Qingni Shen , Zhonghai Wu , Yang Zhang

Deep neural networks (DNNs) have shown unprecedented success in object detection tasks. However, it was also discovered that DNNs are vulnerable to multiple kinds of attacks, including Backdoor Attacks. Through the attack, the attacker…

计算机视觉与模式识别 · 计算机科学 2023-09-19 Yize Cheng , Wenbin Hu , Minhao Cheng

The currently most prominent algorithm to train keyword spotting (KWS) models with deep neural networks (DNNs) requires strong supervision i.e., precise knowledge of the spoken keyword location in time. Thus, most KWS approaches treat the…

声音 · 计算机科学 2023-05-31 Heinrich Dinkel , Weiji Zhuang , Zhiyong Yan , Yongqing Wang , Junbo Zhang , Yujun Wang

With the broad application of deep neural networks (DNNs), backdoor attacks have gradually attracted attention. Backdoor attacks are insidious, and poisoned models perform well on benign samples and are only triggered when given specific…

机器学习 · 计算机科学 2022-07-12 Chang Yue , Peizhuo Lv , Ruigang Liang , Kai Chen

Mainly for the sake of solving the lack of keyword-specific data, we propose one Keyword Spotting (KWS) system using Deep Neural Network (DNN) and Connectionist Temporal Classifier (CTC) on power-constrained small-footprint mobile devices,…

计算与语言 · 计算机科学 2017-09-13 Zhiming Wang , Xiaolong Li , Jun Zhou

Deep neural networks (DNNs) have achieved tremendous success in various applications including video action recognition, yet remain vulnerable to backdoor attacks (Trojans). The backdoor-compromised model will mis-classify to the target…

计算机视觉与模式识别 · 计算机科学 2023-12-12 Xi Li , Songhe Wang , Ruiquan Huang , Mahanth Gowda , George Kesidis

With the widespread use of deep learning system in many applications, the adversary has strong incentive to explore vulnerabilities of deep neural networks and manipulate them. Backdoor attacks against deep neural networks have been…

密码学与安全 · 计算机科学 2019-06-05 Jiazhu Dai , Chuanshuai Chen

We introduce a new attack against face verification systems based on Deep Neural Networks (DNN). The attack relies on the introduction into the network of a hidden backdoor, whose activation at test time induces a verification error…

计算机视觉与模式识别 · 计算机科学 2021-05-04 Wei Guo , Benedetta Tondi , Mauro Barni

Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become increasingly prevalent in many real world applications…

密码学与安全 · 计算机科学 2018-08-31 Cong Liao , Haoti Zhong , Anna Squicciarini , Sencun Zhu , David Miller
‹ 上一页 1 2 3 10 下一页 ›