Cybersecurity Camp II

(Deep learning Security Workshop)

Research Forum, 14 December 2017

The Camp featured a Research Forum to showcase developments at the intersectionof deep learning and security. Students, researchers, and practitioners are invited to submit ‘work-in-progress’ or short research talks. Talks can include emerging hot topics, preliminary research results, practical problems encountered by industry practitioners, lessons learned, exciting datasets, and other topics of interest to security researchers working in deep learning.

-- RESEARCH FORUM: SESSION 1 --

"User Action As An Authentication Mechanism To Improve Smartphone Security"
Arul Prakash Samathuvamani
(View Presentation Slides)

"Privacy Leakage In Long Short Term Memory"
Lun Wang
(View Presentation Slides)

"Attacking The Image Captioning Model - Take Show And Tell Model As An Example "
Jiaqi Tong
(View Presentation Slides)

"Comparative Evaluation Of Synthetic Data Generation Methods "
Ashish Dandekar, Remmy A. M. Zen And Stephane Bressan
(View Presentation Slides)


-- RESEARCH FORUM: SESSION 2 --

"Side-Channel Analysis And Machine Learning: A Practical Perspective"
Sylvain Guilley And Matthieu Lec'hvien
(View Presentation Slides)

"On The Search For Invertible Generative Adversarial Networks"
Jiyi Zhang, Hung Dang, Hwee Kuan Lee And Ee-Chien Chang

"On The Application Of Deep Learning Techniques To Website Fingerprinting Attacks And Defenses"
Marc Juarez And Vera Rimmer
(View Presentation Slides)

"Recovering Types From Binaries"
Teodora Baluta, Shiqi Shen And Alexandros Dimos
(View Presentation Slides)

-- RESEARCH FORUM: SESSION 3 --

"End-To-End Privacy Preserving Hadoop"
Rudrapatna Shyamasundar. Sechadoop
(View Presentation Slides)

"Learning Relations Between Variables Using Deep Learning"
Shiqi Shen And Soundarya Ramesh

"A Try At Task-Based Dialogue Building "
Sishan Long
(View Presentation Slides)

"Early Detection Of Crossfire Attacks Using Deep Learning"
Saurabh Misra, Mengxuan Tan, Mostafa Rezazad And Ngai-Man Cheung
(View Presentation Slides)

"Do We Need Original Data For Training? Toward Designing Privacy-Preserving Machine Learning"
Qingrong Chen, Minhui Xue, Chong Xiang, Bo Li, Haizhong Zheng And Haojin Zhu
(View Presentation Slides)

-- RESEARCH FORUM: SESSION 4 --

"Neural Architecture Search: Insights And Long-Term Horizons"
Mingjie Sun
(View Presentation Slides)

"Noise Data Augmentation For Speaker Recognition Using Conditional Generative Adversarial Networks"
Peiyao Sheng
(View Presentation Slides)

"On Lyapunov Exponents And Adversarial Perturbations "
Vinay Prabhu And John Whaley
(View Presentation Slides)

"Transferability Of Adversarial Attacks In Model-Agnostic Meta-Learning "
Riley Edmunds, Noah Golmant, Vinay Ramasesh, Phillip Kuznetsov, Piyush Patil And Raul Puri
(View Presentation Slides)


Deep Learning Security Workshop, 15 December 2017

The workshop featured invited speakers from Google Research, Alibaba Cloud Security, UnifyID, Georgia Institute of Technology, and National University of Singapore.

"Structure2vec: Deep Learning for Security Analytics over Graphs"
Associate Professor Le Song, Georgia Institute of Technology; Principle Engineer, Ant Financial

-- SESSION I: DEEP LEARNING FOR SECURITY --

"An Implementation of Web Application Firewall Based on a Deep Neural Network Detection Engine"
Mr. Liang Shi, Staff Expert and Manager of Security Data Science team, Alibaba Cloud Security
Mr. Min Ye, Senior Security Expert, Alibaba Cloud Security
Mr. Tianlong Liu, Senior Algorithm Engineer, Alibaba Cloud Security

"Deep Learning for User Authentication "
Dr. John Whaley, Founder and CEO, UnifyID
(View Presentation Slides)

-- SESSION II: SECURITY FOR DEEP LEARNING --

"Data Privacy in Machine Learning"
Dr. Reza Shokri, Assistant Professor, National University of Singapore
(View Presentation Slides)

"Adversarial Deep Learning: Attacks and Defenses"
Dr. Ian Fischer – Researcher, Google Research

"Demo on Biometrics Security"
Mr. Gao Shupeng, Baidu
(View Presentation Slides)



Schedule