Skip to main content

Home

 

Find us on

facebook youtube flickr twitter itunes u logo

Past Talks

Dr. Liz Bowman

Dr. Elizabeth Bowman
U.S. Army Research Laboratory
Artificial Intelligence, Machine Learning and Information: Army Social Computing Research
Tuesday, December 5th
Haldeman 041 Kreindler Conference Room
4:00 PM

Dr. Fabio Pierazzi

Dr. Fabio Pierazzi
Royal Holloway University of London
Network Security Analytics for Detection of Advanced Cyberattacks
Tuesday, November 28th
Sudikoff Trust Lab (L045)
12:30 PM

V.S. Subrahmanian

V.S. Subrahmanian
Dartmouth Distinguished Professor in Cybersecurity, Technology, and Society
Bots, Socks, and Vandals
Tuesday, November 14th
Carson L01
5:00 PM 

Rand Beers

Rand Beers ('64)
Big Data, the Internet, and Social Media:  The Road to the November 2016 Election
Wednesday, November 8th
Haldeman 41 (Kreindler Conference Hall)
4:30 PM 

Fright Night Imge

Wanna See Something REALLY Scary?
ISTS Looks at the Dark Web on Halloween Night
Tuesday, October 31st
S
udikoff  045 Trust Lab (dungeon)
7:30 PM - RSVP
Space is Limited 

Sal Stolfo

Salvatore J. Stolfo 
Columbia University
A Brief History of Symbiote Defense
Tuesday, October 31st
Rockefeller 003
5:00 PM

Dan Wallach

STAR-Vote: A Secure, Transparent, Auditable and Reliable Voting System

Professor Dan Wallach
Rice University
Thursday April 27, 2017
Carson L01, 5:00 PM

Ben Miller Dragos

Pandora's Power Grid - What Can State Attacks Do and What Would be the Impact?

Ben Miller
Chief Threat Officer, Dragos, Inc.
Tuesday May 2, 2017
Kemeny 007, 4:30 PM
Brendan Nyhan

 

 

 

Factual Echo Chambers? Fact-checking and Fake News in Election 2016.

Professor Brendan Nyhan
Dartmouth College
Thursday May 4, 2017
Rocky 001, 5:00 PM

Dickie George

 

Espionage and Intelligence

Professor Dickie George
Johns Hopkins University
Thursday May 11, 2017
Rocky 001, 5:00 PM

Dan Wallach

A Nation Under Attack: Advanced Cyber-Attacks in Ukraine

Ukrainian Cybersecurity Researchers
Thursday April 6, 2017
Oopik Auditorium 5:30 PM

ISTS Information Pamphlet


2012BrochureCover

 

Institute for Security, Technology, and Society
Dartmouth College
6211 Sudikoff Laboratory
Hanover, NH 03755 USA
info.ists@dartmouth.edu
HomeEvents >

Exploiting Feature Distributions in Anomaly Diagnosis

Abstract

Both operators and users of the Internet are increasingly concerned with the problem of network anomalies --- attacks, infections, misconfiguations, and other unusual events. The increasing practicality of large-scale flow capture makes it possible to conceive of traffic analysis methods that detect and identify a large and diverse set of anomalies. However the challenge of effectively analyzing this massive data source for anomaly diagnosis is as yet unmet. In this talk I will argue that the distributions of packet features (IP addresses and ports) observed in flow traces reveals both the presence and the structure of a wide range of anomalies. Using entropy as a summarization tool, I will show that the analysis of feature distributions leads to significant advances on two fronts: (1) it enables highly sensitive detection of a wide range of anomalies, augmenting detections by volume-based methods, and (2) it enables automatic classification of anomalies via unsupervised learning. Using data from two backbone networks (Abilene and Geant), I will show that using feature distributions, anomalies naturally fall into distinct and meaningful clusters. These clusters can be used to automatically classify anomalies and to uncover new anomaly types.