Data Mining for Malicious Code Detection and Security

Data Mining for Malicious Code Detection and Security

Data Mining for Malicious Code Detection and Security Applications Prof. Bhavani Thuraisingham The University of Texas at Dallas March 17, 2008 Lecture #19 02/04/20 02:17 Outline 0 Acknowledgement - Prof. Latifur Khan, Dr. Awad (former PhD student and postdoc at UTD), Mehedy Masud (PhD student) 0 Overview of Data Mining 0 Vision for Assured Information Sharing (Our framework) 0 Data Mining for Cyber security applications - Intrusion Detection

- Data Mining for Assembly code - Data mining for Buffer overflow - Data mining for firewall policy checking - Data mining for email work detection 2 02/04/20 02:17 Vision: Assured Information Sharing Data/Policy for Coalition Publish Data/Policy Publish Data/Policy Publish Data/Policy Component

Data/Policy for Agency A Component Data/Policy for Agency C Component Data/Policy for Agency B 1. Friendly partners 2. Semi-honest partners 3. Untrustworthy partners

3 02/04/20 02:17 4 What is Data Mining? Information Harvesting Knowledge Mining Data Mining Knowledge Discovery in Databases Data Dredging Data Archaeology Data Pattern Processing Database Mining

Siftware Knowledge Extraction The process of discovering meaningful new correlations, patterns, and trends by sifting through large amounts of data, often previously unknown, using pattern recognition technologies and statistical and mathematical techniques (Thuraisingham, Data Mining, CRC Press 1998) 02/04/20 02:17 Whats going on in data mining? 0 What are the technologies for data mining? - Database management, data warehousing, machine learning, statistics, pattern recognition, visualization, parallel processing 0 What can data mining do for you? - Data mining outcomes: Classification, Clustering, Association, Anomaly detection, Prediction, Estimation, . . .

0 How do you carry out data mining? - Data mining techniques: Decision trees, Neural networks, Marketbasket analysis, Link analysis, Genetic algorithms, . . . 0 What is the current status? - Many commercial products mine relational databases 0 What are some of the challenges? - Mining unstructured data, extracting useful patterns, web mining, Data mining, security and privacy 5 02/04/20 02:17 Data Mining for Intrusion Detection: Problem 0 An intrusion can be defined as any set of actions that attempt to compromise the integrity, confidentiality, or availability of a resource.

0 Attacks are: - Host-based attacks - Network-based attacks 0 Intrusion detection systems are split into two groups: - Anomaly detection systems - Misuse detection systems 0 Use audit logs - Capture all activities in network and hosts. - But the amount of data is huge! 6

02/04/20 02:17 Misuse Detection 0 Misuse Detection 7 02/04/20 02:17 Problem: Anomaly Detection 0 Anomaly Detection 8 02/04/20 02:17 Our Approach: Overview 9 Training

Data Class Hierarchical Clustering (DGSOT) SVM Class Training Testing DGSOT: Dynamically growing self organizing tree Testing Data 02/04/20 02:17 Our Approach: Hierarchical Clustering Our Approach Hierarchical clustering with SVM flow chart

10 02/04/20 02:17 11 Results Training Time, FP and FN Rates of Various Methods Average FP Average FN Rate (%) Rate (%)

Accuracy Total Training Time Random Selection 52% 0.44 hours 40 47 Pure SVM 57.6%

17.34 hours 35.5 42 SVM+Rocchio Bundling 51.6% 26.7 hours 44.2 48 SVM + DGSOT 69.8%

13.18 hours 37.8 29.8 Methods Average 02/04/20 02:17 Introduction: Detecting Malicious Executables using Data Mining 0 What are malicious executables? - Harm computer systems - Virus, Exploit, Denial of Service (DoS), Flooder, Sniffer, Spoofer, Trojan etc. - Exploits software vulnerability on a victim

- May remotely infect other victims - Incurs great loss. Example: Code Red epidemic cost $2.6 Billion 0 Malicious code detection: Traditional approach - Signature based - Requires signatures to be generated by human experts - So, not effective against zero day attacks 12 02/04/20 02:17 13 State of the Art in Automated Detection OAutomated detection approaches: 0Behavioural: analyse behaviours like source, destination address,

attachment type, statistical anomaly etc. 0Content-based: analyse the content of the malicious executable - Autograph (H. Ah-Kim CMU): Based on automated signature generation process - N-gram analysis (Maloof, M.A. et .al.): Based on mining features and using machine learning. 02/04/20 02:17 Our New Ideas (Khan, Masud and Thuraisingham) Content -based approaches consider only machine-codes (byte-codes). Is it possible to consider higher-level source codes for malicious code detection?

Yes: Diassemble the binary executable and retrieve the assembly program Extract important features from the assembly program Combine with machine-code features 14 02/04/20 02:17 Feature Extraction Binary n-gram features - Sequence of n consecutive bytes of binary executable Assembly n-gram features

- Sequence of n consecutive assembly instructions System API call features - DLL function call information 15 02/04/20 02:17 The Hybrid Feature Retrieval Model 0 Collect training samples of normal and malicious executables. 0 Extract features 0 Train a Classifier and build a model 0 Test the model against test samples 16

02/04/20 02:17 Hybrid Feature Retrieval (HFR) 0 Training 17 02/04/20 02:17 Hybrid Feature Retrieval (HFR) 0 Testing 18 02/04/20 02:17 Feature Extraction Binary n-gram features - Features are extracted from the byte codes in the form of ngrams, where n = 2,4,6,8,10 and so on. Example:

Given a 11-byte sequence: 0123456789abcdef012345, The 2-grams (2-byte sequences) are: 0123, 2345, 4567, 6789, 89ab, abcd, cdef, ef01, 0123, 2345 The 4-grams (4-byte sequences) are: 01234567, 23456789, 456789ab,...,ef012345 and so on.... Problem: - Large dataset. Too many features (millions!). Solution: - Use secondary memory, efficient data structures - Apply feature selection 19 02/04/20 02:17 Feature Extraction Assembly n-gram features - Features are extracted from the assembly programs in the form of n-grams, where n = 2,4,6,8,10 and so on. Example:

three instructions push eax; mov eax, dword[0f34] ; add ecx, eax; 2-grams (1) push eax; mov eax, dword[0f34]; (2) mov eax, dword[0f34]; add ecx, eax; Problem: - Same problem as binary Solution: - Same solution 20 02/04/20 02:17 21 Feature Selection 0 Select Best K features 0 Selection Criteria: Information Gain

0 Gain of an attribute A on a collection of examples S is given by G a in ( S , A ) E n tro p y ( S ) V V a lu e s ( A ) |Sv | E n tro p y ( S v ) |S | 02/04/20 02:17 22 Experiments 0 Dataset - Dataset1: 838 Malicious and 597 Benign executables

- Dataset2: 1082 Malicious and 1370 Benign executables - Collected Malicious code from VX Heavens ( 0 Disassembly - Pedisassem ( ) 0 Training, Testing - Support Vector Machine (SVM) - C-Support Vector Classifiers with an RBF kernel 02/04/20 02:17 23 Results 0 0

0 HFS = Hybrid Feature Set BFS = Binary Feature Set AFS = Assembly Feature Set 02/04/20 02:17 24 Results 0 0 0 HFS = Hybrid Feature Set BFS = Binary Feature Set AFS = Assembly Feature Set 02/04/20 02:17

25 Results 0 0 0 HFS = Hybrid Feature Set BFS = Binary Feature Set AFS = Assembly Feature Set 02/04/20 02:17 26 Future Plans 0 System call: - seems to be very useful.

Need to Consider Frequency of call Call sequence pattern (following program path) Actions immediately preceding or after call 0 Detect Malicious code by program slicing - requires analysis 02/04/20 02:17 27 Data Mining for Buffer Overflow Introduction 0 Goal - Intrusion detection. - e.g.: worm attack, buffer overflow attack. 0 Main Contribution - 'Worm' code detection by data mining coupled with 'reverse engineering'.

- Buffer overflow detection by combining data mining with static analysis of assembly code. 02/04/20 02:17 28 Background 0 What is 'buffer overflow'? - A situation when a fixed sized buffer is overflown by a larger sized input. 0 How does it happen? - example: ........ char buff[100]; gets(buff); ........

memory Input string buff Stack 02/04/20 02:17 29 Background (cont...) 0 Then what? buff memory ........ char buff[100]; gets(buff); ........

buff Stack Stack Return address overwritten Attacker's code memory buff Stack New return address points to this memory location 02/04/20 02:17 Background (cont...) 0 So what?

- Program may crash or - The attacker can execute his arbitrary code 0 It can now - Execute any system function - Communicate with some host and download some 'worm' code and install it! - Open a backdoor to take full control of the victim 0 How to stop it? 30 02/04/20 02:17 Background (cont...) 0 Stopping buffer overflow - Preventive approaches

- Detection approaches 0 Preventive approaches - Finding bugs in source code. Problem: can only work when source code is available. - Compiler extension. Same problem. - OS/HW modification 0 Detection approaches - Capture code running symptoms. Problem: may require long running time. - Automatically generating signatures of buffer overflow attacks. 31 02/04/20 02:17 CodeBlocker (Our approach) 0 A detection approach

0 Based on the Observation: - Attack messages usually contain code while normal messages contain data. 0 Main Idea - Check whether message contains code 0 Problem to solve: - Distinguishing code from data 32 02/04/20 02:17 Severity of the problem 0 It is not easy to detect actual instruction sequence from a given string of bits 34

02/04/20 02:17 Our solution 0 Apply data mining. 0 Formulate the problem as a classification problem (code, data) 0 Collect a set of training examples, containing both instances 0 Train the data with a machine learning algorithm, get the model 0 Test this model against a new message 35 02/04/20 02:17

CodeBlocker Model 36 02/04/20 02:17 Feature Extraction 37 02/04/20 02:17 Disassembly 0 We apply SigFree tool - implemented by Xinran Wang et al. (PennState) 38 02/04/20 02:17

Feature extraction 39 0 Features are extracted using - N-gram analysis - Control flow analysis 0 N-gram analysis What is an n-gram? -Sequence of n instructions Traditional approach: -Flow of control is ignored 2-grams are: 02, 24, 46,...,CE Assembly program

Corresponding IFG 02/04/20 02:17 Feature extraction (cont...) 0 Control-flow Based N-gram analysis What is an n-gram? -Sequence of n instructions Proposed Control-flow based approach -Flow of control is considered 2-grams are: 02, 24, 46,...,CE, E6 Assembly program Corresponding IFG

40 02/04/20 02:17 Feature extraction (cont...) 0 Control Flow analysis. Generated features - Invalid Memory Reference (IMR) - Undefined Register (UR) - Invalid Jump Target (IJT) 0 Checking IMR - A memory is referenced using register addressing and the register value is undefined - e.g.: mov ax, [dx + 5] 0 Checking UR - Check if the register value is set properly 0 Checking IJT

- Check whether jump target does not violate instruction boundary 41 02/04/20 02:17 Putting it together 0 Why n-gram analysis? - Intuition: in general, disassembled executables should have a different pattern of instruction usage than disassembled data. 0 Why control flow analysis? - Intuition: there should be no invalid memory references or invalid jump targets. 0 Approach

- Compute all possible n-grams - Select best k of them - Compute feature vector (binary vector) for each training example - Supply these vectors to the training algorithm 42 02/04/20 02:17 Experiments 0 Dataset - Real traces of normal messages - Real attack messages - Polymorphic shellcodes 0 Training, Testing - Support Vector Machine (SVM) 43

02/04/20 02:17 Results 0 0 CFBn: Control-Flow Based n-gram feature CFF: Control-flow feature 44 02/04/20 02:17 Novelty, Advantages, Limitations, Future 0 Novelty - We introduce the notion of control flow based n-gram - We combine control flow analysis with data mining to detect code / data - Significant improvement over other methods (e.g. SigFree)

0 Advantages - Fast testing - Signature free operation - Low overhead - Robust against many obfuscations 0 Limitations - Need samples of attack and normal messages. - May not be able to detect a completely new type of attack. 0 Future - Find more features - Apply dynamic analysis techniques - Semantic analysis 45 02/04/20 02:17 Analysis of Firewall Policy Rules Using Data Mining Techniques Firewall is the de facto core technology of todays network security First line of defense against external network attacks and threats

Firewall controls or governs network access by allowing or denying the incoming or outgoing network traffic according to firewall policy rules. Manual definition of rules often result in in anomalies in the policy Detecting and resolving these anomalies manually is a tedious and an error prone task Solutions: Anomaly detection: Theoretical Framework for the resolution of anomaly; A new algorithm will simultaneously detect and resolve any anomaly that is present in the policy rules Traffic Mining: Mine the traffic and detect anomalies 46 02/04/20 02:17 47 Traffic Mining 0 To bridge the gap between what is written in the firewall policy rules

and what is being observed in the network is to analyze traffic and log of the packets traffic mining =Network traffic trend may show that some rules are outdated or not used recently Firewall Policy Rule Firewall Log File Mining Log File Using Frequency Filtering Rule Generalization Edit Firewall Rules

Identify Decaying & Dominant Rules Generic Rules 02/04/20 02:17 Traffic Mining Results 1: TCP,INPUT,,ANY,*.*.*.*,80,DENY 2: TCP,INPUT,*.*.*.*,ANY,*.*.*.*,80,ACCEPT 3: TCP,INPUT,*.*.*.*,ANY,*.*.*.*,443,DENY 4: TCP,INPUT,,ANY,*.*.*.*,22,DENY 5: TCP,INPUT,*.*.*.*,ANY,*.*.*.*,22,ACCEPT 6: TCP,OUTPUT,,ANY,*.*.*.*,22,DENY 7: UDP,OUTPUT,*.*.*.*,ANY,*.*.*.*,53,ACCEPT 8: UDP,INPUT,*.*.*.*,53,*.*.*.*,ANY,ACCEPT 9: UDP,OUTPUT,*.*.*.*,ANY,*.*.*.*,ANY,DENY 10: UDP,INPUT,*.*.*.*,ANY,*.*.*.*,ANY,DENY 11: TCP,INPUT,,ANY,,22,DEN

Y 12: TCP,INPUT,,ANY,,80,DEN Y 13: UDP,INPUT,*.*.*.*,ANY,,ANY,DENY 14: UDP,OUTPUT,,ANY,129.110.10.*,ANY,DE NY 15: TCP,INPUT,*.*.*.*,ANY,,22,ACCEPT 16: TCP,INPUT,*.*.*.*,ANY,,80,ACCEPT 17: UDP,INPUT,129.110.*.*,53,,ANY,ACCEPT 18: 48 Rule 1, Rule 2: ==> GENRERALIZATION Rule 1, Rule 16: ==> CORRELATED Rule 2, Rule 12: ==>

SHADOWED Rule 4, Rule 5: ==> GENRERALIZATION Rule 4, Rule 15: ==> CORRELATED Rule 5, Rule 11: ==> SHADOWED Anomaly Discovery Result 02/04/20 02:17 Worm Detection: Introduction 0 0 0 0

0 0 0 - What are worms? Self-replicating program; Exploits software vulnerability on a victim; Remotely infects other victims Evil worms Severe effect; Code Red epidemic cost $2.6 Billion Goals of worm detection Real-time detection Issues Substantial Volume of Identical Traffic, Random Probing Methods for worm detection Count number of sources/destinations; Count number of failed connection attempts Worm Types

Email worms, Instant Messaging worms, Internet worms, IRC worms, Filesharing Networks worms Automatic signature generation possible EarlyBird System (S. Singh -UCSD); Autograph (H. Ah-Kim - CMU) 49 02/04/20 02:17 Email Worm Detection using Data Mining Task: given some training instances of both normal and viral emails, induce a hypothesis to detect viral emails. We used: Nave Bayes SVM Outgoing Emails

The Model Test data Feature extraction Machine Learning Classifier Training data Clean or Infected ? 50 02/04/20 02:17 Assumptions 0 Features are based on outgoing emails. 0 Different users have different normal behaviour. 0 Analysis should be per-user basis.

0 Two groups of features - Per email (#of attachments, HTML in body, text/binary attachments) - Per window (mean words in body, variable words in subject) 0 Total of 24 features identified 0 Goal: Identify normal and viral emails based on these features 51 02/04/20 02:17 Feature sets - Per email features = Binary valued Features Presence of HTML; script tags/attributes; embedded images; hyperlinks; Presence of binary, text attachments; MIME types of file

attachments = Continuous-valued Features Number of attachments; Number of words/characters in the subject and body - Per window features = Number of emails sent; Number of unique email recipients; Number of unique sender addresses; Average number of words/characters per subject, body; average word length:; Variance in number of words/characters per subject, body; Variance in word length = Ratio of emails with attachments 52 02/04/20 02:17 53 Data Mining Approach Test instance

Clean/ Infected Classifier Test instance SVM infected ? Clean ? Nave Bayes Clean/ Infected

Clean 02/04/20 02:17 Data set 0 Collected from UC Berkeley. - Contains instances for both normal and viral emails. 0 Six worm types: - bagle.f, bubbleboy, mydoom.m, - mydoom.u, netsky.d, sobig.f 0 Originally Six sets of data: - training instances: normal (400) + five worms (5x200) - testing instances: normal (1200) + the sixth worm (200) 0 Problem: Not balanced, no cross validation reported 0 Solution: re-arrange the data and apply cross-validation 54

02/04/20 02:17 Our Implementation and Analysis 0 Implementation - Nave Bayes: Assume Normal distribution of numeric and real data; smoothing applied - SVM: with the parameter settings: one-class SVM with the radial basis function using gamma = 0.015 and nu = 0.1. 0 Analysis - NB alone performs better than other techniques - SVM alone also performs better if parameters are set correctly

mydoom.m and VBS.Bubbleboy data set are not sufficient (very low detection accuracy in all classifiers) - The feature-based approach seems to be useful only when we have identified the relevant features gathered enough training data Implement classifiers with best parameter settings 55

Recently Viewed Presentations

  • Recap - True or False -

    Recap - True or False -

    Recap - True or False. Leibniz's Law states that if two things have all the same properties then they are identical (the same thing). Two pens that are the same colour, shape and have the same ink could be called...
  • Maths at Scott Primary School

    Maths at Scott Primary School

    How Maths is presented in 3 different strands and what is included in each strand; ... Every day Maria uses 50g of oats to make porridge. ... there are lots of games and computer games which have a maths element...
  • Cell Structure -

    Cell Structure -

    CELL STRUCTURE 1 Cell Wall Cell Membrane 2 3 Cytoplasm Nucleus 4 Endoplasmic Reticulum Golgi Body 6 7 Ribosomes Mitochondria 8 9 Lysomes Chloroplast 10 Staple at the top where indicated by a Cut along the dotted line.
  • Fundamentals of Metal Forming ME 482 - Manufacturing

    Fundamentals of Metal Forming ME 482 - Manufacturing

    Fundamentals of Metal Forming Fundamentals of Metal Forming Bulk deformation vs Sheetmetal working Bulk deformation * Low surface area to volume ratios * Operations increase surface area to volume ratios Operations are: rolling extrusion forging drawing This group of machines...
  • Majesty words and music by Martin Smith, Stuart

    Majesty words and music by Martin Smith, Stuart

    Title: Slide 1 Author: Martin Ralston Last modified by: Carol's Created Date: 5/3/2008 4:53:28 PM Document presentation format: On-screen Show (4:3)
  • Learning Goal -

    Learning Goal -

    List the three key concepts of Walter's Lifestyle Theory. Distinguish the difference between psychopathy and sociopathy. Discuss various rehabilitative programs utilized under psychosocial theories. Performance Objectives
  • Atmospheres in the Solar System

    Atmospheres in the Solar System

    Atmospheres in the Solar System Whether a planet has an atmosphere or not depends on the relative magnitude of two speeds The speed at which molecules move around in the gas (thermal speed) The speed of escape from the planet...
  • The Local Food Policy Audit: Spanning the Civic-Political ...

    The Local Food Policy Audit: Spanning the Civic-Political ...

    FCLFC Audit Process. Created audit tool. 100 points divided into four broad categories and 18 subcategories. Promoting . Local Food, Sustainability, and Community Food . Security. Fostering . Social . Equity. Strengthening . Zoning and Land . Use. Addressing ....