2014 Unsupervised Malware Classification: How Bad Software Can Find its own Kind Shannon Steinfadt, Ph.D., Juston Moore, Micah Yates Los Alamos National.

Slides:



Advertisements
Similar presentations
Thank you to IT Training at Indiana University Computer Malware.
Advertisements

SECURITY AND INFORMATION SYSTEMS THE EVOLUTION OF SECURITY SYSTEMS Created By: Jamere Hill Instructor: Kyhia Bostic Section University of Houston.
Malware Identification and Classification
MIS PERSONAL, LEGAL, ETHICAL, AND ORGANIZATIONAL ISSUES OF INFORMATION SYSTEMS CHAPTER 4 Hossein BIDGOLI Phishing that bites Paying for Privacy Pirates.
Content  Overview of Computer Networks (Wireless and Wired)  IP Address, MAC Address and Workgroups  LAN Setup and Creating Workgroup  Concept on.
©TheMcGraw-Hill Companies, Inc. Permission required for reproduction or display. COMPSCI 125 Introduction to Computer Science I.
LittleOrange Internet Security an Endpoint Security Appliance.
Computer Security Fundamentals by Chuck Easttom Chapter 5 Malware.
FIRST COURSE Computer Concepts Internet and Microsoft Office Get to Know Your Computer.
MOBILE MALWARE TOPIC #5 – INFORMATION ASSURANCE AND SECURITY Michael Fine 1.
Course: Introduction to Computers
MIS PERSONAL, LEGAL, ETHICAL, AND ORGANIZATIONAL ISSUES OF INFORMATION SYSTEMS CHAPTER 4 LO1 Describe information technologies that could be used in computer.
Hierarchical file system Hierarchical file system - A hierarchical file system is how drives, folders, and files are displayed on an operating system.
Internet Safety Basics Being responsible -- and safer -- online Visit age-appropriate sites Minimize chatting with strangers. Think critically about.
Henric Johnson1 Chapter 10 Malicious Software Henric Johnson Blekinge Institute of Technology, Sweden
Over the last years, the amount of malicious code (Viruses, worms, Trojans, etc.) sent through the internet is highly increasing. Due to this significant.
1 Chap 10 Malicious Software. 2 Viruses and ”Malicious Programs ” Computer “Viruses” and related programs have the ability to replicate themselves on.
Data Security.
Malicious Code Brian E. Brzezicki. Malicious Code (from Chapter 13 and 11)
APT29 HAMMERTOSS Jayakrishnan M.
Hacker Zombie Computer Reflectors Target.
Business Computing 550 Lesson 6. 2 Security Threats on Web Sites Issues and vulnerabilities 1.Illegal Access and Use (Hacking the system or users exposing.
IT security By Tilly Gerlack.
WHAT IS VIRUS? NAE GRAND CHALLENGE SECURE CYBERSPACE.
Printing: This poster is 48” wide by 36” high. It’s designed to be printed on a large-format printer. Customizing the Content: The placeholders in this.
‘Tirgul’ # 7 Enterprise Development Using Visual Basic 6.0 Autumn 2002 Tirgul #7.
1 What is a computer virus? Computer program Replicating Problematic "Event" Types Detection and prevention.
Chapter 10 Malicious software. Viruses and ” Malicious Programs Computer “ Viruses ” and related programs have the ability to replicate themselves on.
Here is a list of viruses Adware- or advertising-supported software-, is any software package which automatically plays, displays, or downloads advertisements.
Automated Classification and Analysis of Internet Malware M. Bailey J. Oberheide J. Andersen Z. M. Mao F. Jahanian J. Nazario RAID 2007 Presented by Mike.
Interception and Analysis Framework for Win32 Scripts (not for public release) Tim Hollebeek, Ph.D.
Basic of Programming Language Skill Area Computer System Computer Program Programming Language Programmer Translators.
Understanding Computer Viruses: What They Can Do, Why People Write Them and How to Defend Against Them Computer Hardware and Software Maintenance.
Using Engine Signature to Detect Metamorphic Malware Mohamed R. Chouchane and Arun Lakhotia Software Research Laboratory The University of Louisiana at.
Security Analytics Thrust Anthony D. Joseph (UCB) Rachel Greenstadt (Drexel), Ling Huang (Intel), Dawn Song (UCB), Doug Tygar (UCB)
Disclaimer The Content, Demonstration, Source Code and Programs presented here is "AS IS" without any warranty or conditions.
n Just as a human virus is passed from person from person, a computer virus is passed from computer to computer. n A virus can be attached to any file.
Intrusion Detection Systems Paper written detailing importance of audit data in detecting misuse + user behavior 1984-SRI int’l develop method of.
Understand Malware LESSON Security Fundamentals.
A global nonprofit: Focusing on IP Protection and Anti-Corruption Sharing leading practices based on insights from global companies, academics, organizations.
Types of Malware © 2014 Project Lead The Way, Inc.Computer Science and Software Engineering.
© 2007 Cisco Systems, Inc. All rights reserved.Cisco Public ITE PC v4.0 Chapter 1 1 Basic Security Networking for Home and Small Businesses – Chapter 8.
Page 1 Viruses. Page 2 What Is a Virus A virus is basically a computer program that has been written to perform a specific set of tasks. Unfortunately,
By: Jasmin Smith  ability to control what information one reveals about one’s self over the Internet.
COMPUTER VIRUSES Computer Technology. What is a Computer Virus? A kind of A kind of Malicious software written intentionallyMalicious software written.
ANTIVIRUS ANTIVIRUS Author: Somnath G. Kavalase Junior Software developer at PBWebvsion PVT.LTD.
1. ABSTRACT Information access through Internet provides intruders various ways of attacking a computer system. Establishment of a safe and strong network.
Threats To Data 30 Threats To Data 30. Threats To Data 30 We’re now going to look at a range of different threats to people’s data: Opportunity Threats.
Software Reverse Engineering Binary analysis: concepts, methods and tools. Catalin Patulea Mar 5, 2008.
Antivirus Software Technology By Mitchell Zell. Intro  Computers are vulnerable to attack  Most common type of attack is Malware  Short for malicious.
2014 Various Approaches to Malware Detection & Analysis Nidhi Rastogi PhD CS candidate, Rensselaer Polytechnic Institute (RPI), Troy, NY October 9, 2014.
Cosc 4765 Antivirus Approaches. In a Perfect world The best solution to viruses and worms to prevent infected the system –Generally considered impossible.
Abusing 3rd-Party Services For Command And Control
Malware malicious software which is specifically designed to disrupt, damage, or gain authorized access to a computer system Analysis detailed examination.
CYBER SECURITY...
Various Types of Malware
Unit 11 Task #1 Read the unit specification and create a glossary which defines each of the words / terms you don’t know.
Across the world McAfee providing the update protection solutions to the computer users. As same to the error above, wait for few minutes and think some.
Across the world McAfee providing the update protection solutions to the computer users. As same to the error above, wait for few minutes and think some.
Across the world McAfee providing the update protection solutions to the computer users. As same to the error above, wait for few minutes and think some.
Across the world McAfee providing the update protection solutions to the computer users. As same to the error above, wait for few minutes and think some.
Across the world McAfee providing the update protection solutions to the computer users. As same to the error above, wait for few minutes and think some.
ACROSS THE WORLD MCAFEE PROVIDING THE UPDATE PROTECTION SOLUTIONS TO THE COMPUTER USERS. AS SAME TO THE ERROR ABOVE, WAIT FOR FEW MINUTES AND THINK SOME.
Risk of the Internet At Home
Malware, Phishing and Network Policies
Cambridge National Certificate in Information Technologies
(Discussion – The Department of Defense)
Hardware Security – Highlevel Survey Review for Exam 4
Talking Malware Analysis with MITRE
Counter APT Counter APT HUNT operations combine best of breed endpoint detection response technology with an experienced cadre of cybersecurity experts.
Presentation transcript:

2014 Unsupervised Malware Classification: How Bad Software Can Find its own Kind Shannon Steinfadt, Ph.D., Juston Moore, Micah Yates Los Alamos National Laboratory October 9, 2014 Released under LA-UR #GHC

What is Malware?  Malicious software = Malware −Intentional or Unintentional −Includes: Computer viruses Worms Trojan horses Ransomware Spyware Adware Scareware Poorly written software

2014 Growth of Malware  Growth of malware now exceeds legitimate software releases −According to FireEye: “Enterprises experience a malware event up to once every three minutes” (2013)  Mobile applications – new digital frontier of hacking

2014 (Some) Impacts of Malware  Financial impacts −Target −Home Depot −Banks  Intellectual Property −Advanced science knowledge −Patented processes and concepts  Business Impacts −Competitors with insider information −Loss of customers (Neiman Marcus)

2014 Finding Malware  Time consuming  Highly skilled labor required  Difficult task −Easy to overlook −Hard to discern what it is doing Obfuscate true C2 channels Change behavior in VMs  Reverse Engineering (RE)

2014 Classifying Malware  To find (detect) malware, it’s easier if you already know something about existing malware −Code reuse is common across different malicious software files  Would like to have an automatic detection capability but… −What happens after you find malware?

2014 Disassembly  Example executable file suspect as malicious (.exe or.dll)  How to “look under the hood?” −Disassembler (IDA, Olly Debug, …) −Get x86 assembly instructions and some organization by function calls call sub_4300A1 call sub_ test eax, eax jnz short loc_43124F push offset aSFatalError call sub_406B06 pop ecx mov esi, eax

2014 IDA Disassembler View

2014 APT-1  February 2013 – Security company Mandiant released APT1 report −“APT1: Exposing One of China's Cyber Espionage Units” −APT = Advanced Persistent Threat −Data used here is well studied and publically available at −Great for data validation for new tool sets

2014 Detecting Malware in Real Time  Create signatures −Common to malware / unique otherwise −Output format, something that can be fed directly into other systems for detection Snort Rules Bro Rules YARA Rules* −Example YARA Rule from APT-1: rule lightbolt : apt { strings: $a = "bits.exe a all.jpg.\\ALL -hp%s" $b = "The %s store has been opened" $c = "Machine%d" $d = "Service%d" $e = "7z;ace;arj;bz2;cab;gz;jpeg;jpg;lha;lzh;mp3;rar;taz;tgz;z;zip" condition: filesize < 300KB and (5 of ($a,$b,$c,$d,$e)) }

2014 Detecting Malware in Real Time  Create signatures −Common to malware / unique otherwise −Output format, something that can be fed directly into other systems for detection Snort Rules Bro Rules YARA Rules* −Example YARA Rule from APT-1: rule tarsip_eclipse : apt { strings: $a = "Eclipse" $b = "PIGG" $c = "WAKPDT" $d = "show.asp?" $e = "flink?" condition: filesize < 300KB and (5 of ($a,$b,$c,$d,$e)) }

2014 RED/UCE Tool  Reverse Engineering Deduction / Universal Classifying Engine −Suite of tools  Two main tools currently, more in the near future −Visual clustering of software samples and sample exploration −Signature generation for detection of certain families of software (YARA Rules)

2014 RED/UCE Clustering Map  Input: Clean OS files + Small set of malware samples −RED/UCE can assist to make inferences about the authorship of unknown samples

2014 Malware Binaries Clean Binaries IDA Pro Clean Sample 1 wildcarded functions Malware Sample 1 wildcarded functions Clean Sample 2 wildcarded functions … Malware Sample 2 wildcarded functions … Strings Extractor Clean Sample 1 strings Malware Sample 1 strings Clean Sample 2 strings … Malware Sample 2 strings … Counter Count per sample of: Strings Words Functions Basic Blocks Select samples of interest Select samples to compare against Information Gain Sorter Display Feature Lists Strings Words Functions Basic Blocks Select features Generate YARA rule Select thresholds Select a samples for exploration Select meta-groups to compare with Select Features based on clean samples and meta-groups YARA generatorNew Sample Visualizer Identify K clusters to the sample of interest Embed samples in a 2D space using Multidimensional Scaling Display samples with edges connecting them. Each edge shall be annotated with the features in common between sampels.

2014 Count per sample of: Strings Words Functions Basic Blocks Select samples of interest Select samples to compare against Information Gain Sorter Display Feature Lists Strings Words Functions Basic Blocks Select features Generate YARA rule Select thresholds Select a samples for exploration Select meta-groups to compare with Select Features based on clean samples and meta-groups YARA generator New Sample Visualizer Identify K clusters to the sample of interest Embed samples in a 2D space using Multidimensional Scaling Display samples with edges connecting them. Each edge shall be annotated with the features in common between sampels.

2014 RED/UCE Clustering Map

2014 RED/UCE Clustering Map rule tarsip_eclipse : apt { strings: $a = "Eclipse” $b = "PIGG” $c = "WAKPDT" $d = "show.asp?" $e = "flink?” condition: filesize<300KB and (5 of ($a,$b,$c,$d,$e)) }

2014 RED/UCE Clustering Map rule tarsip_eclipse : apt { strings: $a = "Eclipse” $b = "PIGG” $c = "WAKPDT" $d = "show.asp?" $e = "flink?” condition: filesize<300KB and (5 of ($a,$b,$c,$d,$e)) }

2014 RED/UCE Focused Clustering  Focused feature selection set – reduced sample input −Green dot – sample of interest −Red dot – labeled malware sample(s) −Blue dot – labeled good sample(s)

2014 RED/UCE Signature Creation Chosen features (drop-and-drag) Visual output for chosen features

2014 RED/UCE

2014 RED/UCE

2014 RED/UCE Signature Creation

2014 RED/UCE Signature Creation  Common YARA style rule found across all 9 samples −String " c7 ?? ?? ?? ?? ?? 83 c ?? ” −A common basic block across 100% of these samples (Score: 100) {c7 ?? ?? ?? ?? ?? 83 c ??}

2014 Signature Use  Output from RED/UCE can be deployed rapidly in operational environments −Open-source YARA format for signatures currently YARA signatures are commonly used by the security community Tool can be extended to produce other IDS (intrusion detection system) formats Bro, Snort / Sourcefire, …

2014 Conclusions  RED/UCE tool assists analysts to: −Secure their networks from malicious software and users −Quickly find correlations across decompiled software code −Create effective signatures for new, emerging threats  The signature development process is guided by information theoretic principles −Unlike other machine learning systems, RED/UCE provides the analyst with the ability to control the selection of signatures based on operational awareness criteria (knowing what’s important to your institutions)  The tool and signatures can be widely deployed and promote collaboration between other sites −Does not require any vendor-specific hardware or network configuration in order to be useful

2014 Looking for an Internship?  Visit the Los Alamos National Laboratory Table here at GHC’14  Contact if you are  for other opportunities Released under LA-UR

2014 Intel x86 Assembler Instruction Set Opcodes  c7 MOV  83 SUB  c0 #2  04 ADD  41 INC eCX  75 JNZ  ?? Register value (Score: 100) {c7 ?? ?? ?? ?? ?? 83 c ??}

2014 Got Feedback? Rate and Review the session using the GHC Mobile App To download visit