Cutting-Splicing data augmentation: A novel technology for medical image segmentation

no code implementations • 17 Oct 2022 • Lianting Hu, Huiying Liang, Jiajie Tang, Xin Li, Li Huang, Long Lu

Background: Medical images are more difficult to acquire and annotate than natural images, which results in data augmentation technologies often being used in medical image segmentation tasks.

Data Augmentation Image Segmentation +4

SCRUTINIZER: Detecting Code Reuse in Malware via Decompilation and Machine Learning

1 code implementation • International Conference on Detection of Intrusions and Malware, and Vulnerability Assessment 2021 • Omid Mirzaei, Roman Vasilenko, Engin Kirda, Long Lu, Amin Kharraz

In response to such attacks, both academia and industry have investigated techniques to model and reconstruct these attacks and to defend against them.

BIG-bench Machine Learning Code Reuse Detection +1

ShadowNet: A Secure and Efficient On-device Model Inference System for Convolutional Neural Networks

no code implementations • 11 Nov 2020 • Zhichuang Sun, Ruimin Sun, Changming Liu, Amrita Roy Chowdhury, Long Lu, Somesh Jha

ShadowNet protects the model privacy with Trusted Execution Environment (TEE) while securely outsourcing the heavy linear layers of the model to the untrusted hardware accelerators.

DICE: Automatic Emulation of DMA Input Channels for Dynamic Firmware Analysis

2 code implementations • 3 Jul 2020 • Alejandro Mera, Bo Feng, Long Lu, Engin Kirda, William Robertson

We present DICE, a drop-in solution for firmware analyzers to emulate DMA input channels and generate or manipulate DMA inputs.

Cryptography and Security

MEUZZ: Smart Seed Scheduling for Hybrid Fuzzing

1 code implementation • 20 Feb 2020 • Yao-Hui Chen, Mansour Ahmadi, Reza Mirzazade farkhani, Boyu Wang, Long Lu

Seed scheduling is a prominent factor in determining the yields of hybrid fuzzing.

BIG-bench Machine Learning Scheduling

Mind Your Weight(s): A Large-scale Study on Insufficient Machine Learning Model Protection in Mobile Apps

1 code implementation • 18 Feb 2020 • Zhichuang Sun, Ruimin Sun, Long Lu, Alan Mislove

We found that, alarmingly, 41% of ML apps do not protect their models at all, which can be trivially stolen from app packages.

Face Recognition Malware Detection

SAVIOR: Towards Bug-Driven Hybrid Testing

no code implementations • 18 Jun 2019 • Yao-Hui Chen, Peng Li, Jun Xu, Shengjian Guo, Rundong Zhou, Yulong Zhang, Taowei, Long Lu

Unlike the existing hybrid testing tools, SAVIOR prioritizes the concolic execution of the seeds that are likely to uncover more vulnerabilities.

Software Engineering

PTrix: Efficient Hardware-Assisted Fuzzing for COTS Binary

1 code implementation • 25 May 2019 • Yao-Hui Chen, Dongliang Mu, Jun Xu, Zhichuang Sun, Wenbo Shen, Xinyu Xing, Long Lu, Bing Mao

This poor performance is caused by the slow extraction of code coverage information from highly compressed PT traces.

Software Engineering Cryptography and Security