Workshop Program (WiseML)

Pre-conference Workshop/Tutorial Day: Tuesday, May 14th

7:30 – 8:15 – Breakfast

8:15 – 9:10 – Introductions and Keynote

• Keynote: AI/ML and Wireless Security
  Prof. K.P. (Suba) Subbalakshmi (Stevens Institute of Technology)

9:10 – 10:00 – Machine Learning Applications – 1 (Session Chair – Yalin Sagduyu)

• Machine Learning for RF Signal Processing: Catching the Third Wave
  George Stantchev (Naval Research Lab)
• Deep Learning for Wireless Jamming Attacks
  Tugba Erpek (Intelligent Automation Inc. and Virginia Tech)
• Wireless Network Virtualization by Leveraging Blockchain Technology and Machine Learning
  Ashish Adhikari (Howard University), Danda B. Rawat (Howard University), Min Song (Stevens Institute of Technology)

10:00 – 10:20 – Break

10:20 – 11:20 – Adversarial Machine Learning – 1 (Session Chair – Gunes Kurt)

• Generative Adversarial Network for Wireless Signal Spoofing
  Yi Shi (Intelligent Automation Inc.), Kemal Davaslioglu (Intelligent Automation Inc.), Yalin Sagduyu (Intelligent Automation Inc.)
• Generative Adversarial Radio Spectrum Networks
  Tamoghna Roy (DeepSig), Tim O’Shea (DeepSig and Virginia Tech), Nathan West (DeepSig)
• Targeted Adversarial Examples against RF Deep Classifiers
  Silvija Kokalj-Filipovic (Perspecta Labs), Rob Miller (Perspecta Labs), Joshua Morman (Perspecta Labs)

11:20 – 12:20 – Defense with Machine Learning – 1 (Session Chair – Miao Yao)

• Machine Learning-based Prevention of Battery-oriented Illegitimate Task Injection in Mobile Crowdsensing
  Yueqian Zhang (University of Ottawa), Murat Simsek (University of Ottawa), Burak Kantarci (University of Ottawa)
• Jammer Detection based on Artificial Neural Networks: A Measurement Study
  Selen Gecgel (Istanbul Technical University), Caner Goztepe (Istanbul Technical University), Gunes Kurt (Istanbul Technical University)
• Quick and Accurate Detection and Mitigation of IoT-empowered Cyberattacks
  Yasin Yılmaz (University of South Florida)

12:20 – 1:40 – Lunch
13:40 – 14:35 – Machine Learning Applications – 2 (Session Chair – Yasin Yılmaz)

• Testing the Resilience of CNN Implementations
  Alan Michaels (Virginia Tech)
• Threat is in the Air: Machine Learning for Wireless Network Applications
  Luca Pajola (University of Padova), Luca Pasa (Istituto Italiano di Tecnologia), Mauro Conti (University of Padova)
• Introducing Students to Research in Radio Frequency Machine Learning Applications
  William C. Headley (Virginia Tech)

14:35 – 15:30 – Adversarial Machine Learning – 2 (Session Chair – Rob Miller)

• On the Limitations of Targeted Adversarial Evasion Attacks Against Deep Learning Enabled Modulation Recognition
  Samuel Bair (Virginia Tech), Matthew Delvecchio (Virginia Tech), Bryse Flowers (Virginia Tech), Alan J. Michaels (Virginia Tech), William C. Headley (Virginia Tech)
• Efficient Power Adaptation against Deep Learning Based Predictive Adversaries
  Ertugrul Ciftcioglu (Thinkful), Mike Ricos (Thinkful)
• Adversarial RFML: Threats to Deep Learning Enabled Cognitive Radio
  Bryse Flowers (Virginia Tech)

15:30 – 15:50 – Break
15:50 – 16:55 – Defense with Machine Learning – 2 (Session Chair – Matthew Vondal)

• Towards Adversarial and Unintentional Collisions Detection Using Deep Learning
  Hai N. Nguyen (Northeastern University), Tien Vo-Huu (Northeastern University), Triet Vo-Huu (Northeastern University), Guevara Noubir (Northeastern University)
• RAPID: Real-time Anomaly-based Preventive Intrusion Detection
  Keval Doshi (University of South Florida), Mahsa Mozaffari (University of South Florida), Yasin Yilmaz (University of South Florida)
• Detecting Drones Status via Encrypted Traffic Analysis
  Savio Sciancalepore, (Hamad Bin Khalifa University), Omar Adel Ibrahim, (Hamad Bin Khalifa University), Gabriele Oligeri (Hamad Bin Khalifa University), Roberto Di Pietro, (Hamad Bin Khalifa University)

16:55 – 17:50 – Machine Learning Applications – 3 (Session Chair – Yi Shi)

• Robust Signal Classification Using Siamese Networks
  Zachary Langford (Virginia Tech), Logan Eisenbeiser (Virginia Tech), Matthew Vondal (Virginia Tech)
• Contextual Combinatorial Bandit Learning for Online Decision Making Under Uncertainty
  Jie Xu (University of Miami)
• Artificial Intelligence Defined 5G New Radio Networks: Perspective of Industry
  Miao Yao (Qualcomm)