Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Junfeng Yang

Adversarial Attacks are Reversible with Natural Supervision


Mar 29, 2021
Chengzhi Mao, Mia Chiquier, Hao Wang, Junfeng Yang, Carl Vondrick


  Access Paper or Ask Questions

Trex: Learning Execution Semantics from Micro-Traces for Binary Similarity


Dec 29, 2020
Kexin Pei, Zhou Xuan, Junfeng Yang, Suman Jana, Baishakhi Ray

* To appear in 42nd IEEE Symposium on Security and Privacy (Oakland S&P 2021) 

  Access Paper or Ask Questions

Generative Interventions for Causal Learning


Dec 22, 2020
Chengzhi Mao, Amogh Gupta, Augustine Cha, Hao Wang, Junfeng Yang, Carl Vondrick


  Access Paper or Ask Questions

What Does CNN Shift Invariance Look Like? A Visualization Study


Nov 09, 2020
Jake Lee, Junfeng Yang, Zhangyang Wang

* Presented at the 2020 ECCV Workshop on Real-World Computer Vision from Inputs with Limited Quality (RLQ-TOD 2020), Glasgow, Scotland 

  Access Paper or Ask Questions

XDA: Accurate, Robust Disassembly with Transfer Learning


Oct 27, 2020
Kexin Pei, Jonas Guan, David Williams-King, Junfeng Yang, Suman Jana

* To appear in 2021 Network and Distributed System Security Symposium (NDSS 2021) 

  Access Paper or Ask Questions

Multitask Learning Strengthens Adversarial Robustness


Jul 14, 2020
Chengzhi Mao, Amogh Gupta, Vikram Nitin, Baishakhi Ray, Shuran Song, Junfeng Yang, Carl Vondrick


  Access Paper or Ask Questions

Live Trojan Attacks on Deep Neural Networks


May 27, 2020
Robby Costales, Chengzhi Mao, Raphael Norwitz, Bryan Kim, Junfeng Yang


  Access Paper or Ask Questions

AdvSPADE: Realistic Unrestricted Attacks for Semantic Segmentation


Nov 19, 2019
Guangyu Shen, Chengzhi Mao, Junfeng Yang, Baishakhi Ray


  Access Paper or Ask Questions

Unrestricted Adversarial Attacks for Semantic Segmentation


Oct 09, 2019
Guangyu Shen, Chengzhi Mao, Junfeng Yang, Baishakhi Ray


  Access Paper or Ask Questions

Metric Learning for Adversarial Robustness


Sep 03, 2019
Chengzhi Mao, Ziyuan Zhong, Junfeng Yang, Carl Vondrick, Baishakhi Ray


  Access Paper or Ask Questions

NEUZZ: Efficient Fuzzing with NeuralProgram Smoothing


Nov 04, 2018
Dongdong She, Kexin Pei, Dave Epstein, Junfeng Yang, Baishakhi Ray, Suman Jana


  Access Paper or Ask Questions

Efficient Formal Safety Analysis of Neural Networks


Oct 26, 2018
Shiqi Wang, Kexin Pei, Justin Whitehouse, Junfeng Yang, Suman Jana

* Accepted to NIPS'18 

  Access Paper or Ask Questions

Formal Security Analysis of Neural Networks using Symbolic Intervals


Jul 01, 2018
Shiqi Wang, Kexin Pei, Justin Whitehouse, Junfeng Yang, Suman Jana

* Accepted to USENIX Security 2018 

  Access Paper or Ask Questions

Towards Practical Verification of Machine Learning: The Case of Computer Vision Systems


Dec 16, 2017
Kexin Pei, Yinzhi Cao, Junfeng Yang, Suman Jana

* 16 pages, 11 tables, 11 figures 

  Access Paper or Ask Questions

DeepXplore: Automated Whitebox Testing of Deep Learning Systems


Sep 24, 2017
Kexin Pei, Yinzhi Cao, Junfeng Yang, Suman Jana

* To be published in SOSP'17 

  Access Paper or Ask Questions