yingbo

Profile

Full name: 
Yingbo Song
Personal site: 
Personal site
Profile picture: 
Bio: 
Yingbo Song is a PhD student. His research is in machine learning, network security and their intersection in intrusion detection systems. His current research focus is on web-layer code-injection detection using off-host sensors, machine learning models for anomaly detection in network flows and shellcode polymorphism.
Status: 
PhD student

History

Member for
46 weeks 1 day

Associated publications

"Behavior-Based Network Traffic Synthesis,"
Homeland Security Technologies Conference (HST)
2011/11/15
"Brave New World: Pervasive Insecurity of Embedded Network Devices,"
Poster in the 12th Annual International Symposium on Advances in Intrusion Detection (RAID)
2009/09/15
"Spectrogram: A Mixture-of-Markov-Chains Model for Anomaly Detection in Web Traffic,"
Proceedings of the 16th Annual Network & Distributed System Security Symposium (NDSS)
2009/02
"On the Infeasibility of Modeling Polymorphic Shellcode: Re-thinking the Role of Learning in Intrusion Detection Systems,"
Machine Learning Journal. Special issue on adversarial learning
2009
"Density Estimation under Independent Similarly Distributed Sampling Assumptions,"
Proceedings of the 21st Conference on Neural Information Processing Systems (NIPS)
2007/12/04
"Independent Similarly Distributed Sampling Assumptions for Semi-parametric Density Estimation,"
2nd New York Academy of Sciences Symposium on Machine Learning
2007/10/12
"On the Infeasibility of Modeling Polymorphic Shellcode,"
Proceedings of the 14th ACM Conference on Computer and Communications Security (CCS)
2007/10
"Spectral Clustering and Embedding with Hidden Markov Models,"
Proceedings of the 18th European Conference on Machine Learning (ECML)
2007/09/01