48 citations · 57 across the 4 of their papers we have counts for
4 papers
On the Permanence of Backdoors in Evolving Models
Huiying Li, Arjun Nitin Bhagoji, Yuxin Chen +2
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…
Understanding the Effectiveness of Ultrasonic Microphone Jammer
Yuxin Chen, Huiying Li, Steven Nagels +4
Recent works have explained the principle of using ultrasonic transmissions to jam nearby microphones. These signals are inaudible to nearby users, but leverage "hardware nonlinear…
Addressing Training Bias via Automated Image Annotation
Zhujun Xiao, Yanzi Zhu, Yuxin Chen +3
Build accurate DNN models requires training on large labeled, context specific datasets, especially those matching the target scenario. We believe advances in wireless localization…
Et Tu Alexa? When Commodity WiFi Devices Turn into Adversarial Motion Sensors
Yanzi Zhu, Zhujun Xiao, Yuxin Chen +4
Our work demonstrates a new set of silent reconnaissance attacks, which leverages the presence of commodity WiFi devices to track users inside private homes and offices, without co…