66 citations · 108 across the 12 of their papers we have counts for
13 papers
Trainable Projected Gradient Method for Robust Fine-tuning
Junjiao Tian, Xiaoliang Dai, Chih-Yao Ma +3
Recent studies on transfer learning have shown that selectively fine-tuning a subset of layers or customizing different learning rates for each layer can greatly improve robustness…
SoK: Hardware Defenses Against Speculative Execution Attacks
Guangyuan Hu, Zecheng He, Ruby Lee
Speculative execution attacks leverage the speculative and out-of-order execution features in modern computer processors to access secret data or execute code that should not be ex…
Medical Aegis: Robust adversarial protectors for medical images
Qingsong Yao, Zecheng He, S. Kevin Zhou
Deep neural network based medical image systems are vulnerable to adversarial examples. Many defense mechanisms have been proposed in the literature, however, the existing defenses…
CloudShield: Real-time Anomaly Detection in the Cloud
Zecheng He, Ruby B. Lee
In cloud computing, it is desirable if suspicious activities can be detected by automatic anomaly detection systems. Although anomaly detection has been investigated in the past, i…
Smartphone Impostor Detection with Behavioral Data Privacy and Minimalist Hardware Support
Guangyuan Hu, Zecheng He, Ruby B. Lee
Impostors are attackers who take over a smartphone and gain access to the legitimate user's confidential and private information. This paper proposes a defense-in-depth mechanism t…
ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces
Zecheng He, Srinivas Sunkara, Xiaoxue Zang +7
As mobile devices are becoming ubiquitous, regularly interacting with a variety of user interfaces (UIs) is a common aspect of daily life for many people. To improve the accessibil…
A Hierarchical Feature Constraint to Camouflage Medical Adversarial Attacks
Qingsong Yao, Zecheng He, Yi Lin +3
Deep neural networks (DNNs) for medical images are extremely vulnerable to adversarial examples (AEs), which poses security concerns on clinical decision making. Luckily, medical A…
New Models for Understanding and Reasoning about Speculative Execution Attacks
Zecheng He, Guangyuan Hu, Ruby Lee
Spectre and Meltdown attacks and their variants exploit hardware performance optimization features to cause security breaches. Secret information is accessed and leaked through cov…
Miss the Point: Targeted Adversarial Attack on Multiple Landmark Detection
Qingsong Yao, Zecheng He, Hu Han +1
Recent methods in multiple landmark detection based on deep convolutional neural networks (CNNs) reach high accuracy and improve traditional clinical workflow. However, the vulnera…
Smartphone Impostor Detection with Built-in Sensors and Deep Learning
Guangyuan Hu, Zecheng He, Ruby Lee
In this paper, we show that sensor-based impostor detection with deep learning can achieve excellent impostor detection accuracy at lower hardware cost compared to past work on sen…
VerIDeep: Verifying Integrity of Deep Neural Networks through Sensitive-Sample Fingerprinting
Zecheng He, Tianwei Zhang, Ruby B. Lee
Deep learning has become popular, and numerous cloud-based services are provided to help customers develop and deploy deep learning applications. Meanwhile, various attack techniqu…
Privacy-preserving Machine Learning through Data Obfuscation
Tianwei Zhang, Zecheng He, Ruby B. Lee
As machine learning becomes a practice and commodity, numerous cloud-based services and frameworks are provided to help customers develop and deploy machine learning applications.…
Power-Grid Controller Anomaly Detection with Enhanced Temporal Deep Learning
Zecheng He, Aswin Raghavan, Guangyuan Hu +2
Controllers of security-critical cyber-physical systems, like the power grid, are a very important class of computer systems. Attacks against the control code of a power-grid syste…