jim geovedi - machine learning for cybersecurity

38
GVDJ #IDSECCONF2016 machine learning for cybersecurity

Upload: idsecconf

Post on 13-Feb-2017

238 views

Category:

Technology


0 download

TRANSCRIPT

Page 1: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

machine learning for cybersecurity

Page 2: Jim Geovedi - Machine Learning for Cybersecurity
Page 3: Jim Geovedi - Machine Learning for Cybersecurity
Page 4: Jim Geovedi - Machine Learning for Cybersecurity

USA SOUTH KOREA

NORTH KOREA INDONESIA

Page 5: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

security goals

▸ security goals

▸ confidentiality of information and resources

▸ integrity of information and resources

▸ availability of information and resources

▸ basic definitions

▸ threat: potential violation of a security goal

▸ security: protection from intentional threats

▸ attack: intentional violation of a security goal

Page 6: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

security mechanisms

▸ security policies and mechanisms

▸ policy: statement of what is and what is not allowed

▸ mechanism: method or tool enforcing a security policy

▸ security is a process, not a product!

▸ strategies for security mechanisms

▸ prevention of attacks, e.g. encryption

▸ detection of attacks, e.g. virus scanner

▸ analysis of attacks, e.g. forensic

Page 7: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

prevention is a hard task

▸ continuous discovery of vulnerabilities

▸ insecure software and hardware

▸ developers unawareness

goto fail;goto fail;

goto fail(february 2014)

heartbleed(april 2014)

shellshock(september 2014)

Page 8: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

attacks against services

▸ numerous security breaches at popular web services

▸ identities often include real names, addresses, emails, passwords, etc.

‘;--have i been pwned?

142pwned websites

1,444,567,928pwned accounts

39,842pastes

31,108,929paste accounts

Page 9: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

imbalance of security cycle

▸ increasing imbalance of security cycle

▸ increasing number of vulnerabilities

▸ high amount of novel attacks

▸ high diversity of malicious software

▸ bottleneck: human analyst in the loop

▸ manual discovery of vulnerabilities

▸ manual generation of attack signatures

▸ manual analysis of malicious software

Page 10: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

conventional detection

▸ conventional attack detection using signatures

▸ ineffective against novel and unknown attacks

▸ inherent delay to availability of novel signatures

▸ analysis obstructed by polymorphism and obfuscation

HEADER APPLICATION PAYLOAD

... IP TCP GET /scripts/ ..%c1%9c.. /system32/cmd.exe

TCP ..%c1%9c.. NIMDA WORM

Page 11: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

intelligent defence

▸ construction of intelligent security systems

▸ combining computer security and machine learning

▸ minimum human intervention on prevention, detection, and analysis

▸ challenge in practice

▸ effectivity, efficiency, and robustness

▸ transparency and controlability

Page 12: Jim Geovedi - Machine Learning for Cybersecurity

machine learning for cybersecurity

Page 13: Jim Geovedi - Machine Learning for Cybersecurity
Page 14: Jim Geovedi - Machine Learning for Cybersecurity

MACHINELEARNING

PREDICTIONPLATFORM

HUMANINTUITION

Page 15: Jim Geovedi - Machine Learning for Cybersecurity

attack mitigation issues

supervised unsupervised

rules driven(limited by experiences and expertise)

high rates undetectable attacks(false negatives)

delayed response(between detection and prevention)

statistical driven(improved detection of new attacks)

substantial investigative efforts (false positives)

alarm fatigue and distrust(reversion to supervised method)

Page 16: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

implementation challenges

▸ lack of data: limited or no history of previous attacks (required by supervised learning model)

▸ evolving attacks: attackers constantly change their behaviours, making current models obsolete

▸ limited resources: relying on security analysts to investigate the attacks can be costly and time consuming

Page 17: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

components

THREAT PREDICTION PLATFORM

MODEL

ANALYSTS

PREDICTIONFEATURE

RAWDATA ACTION

EVENTSMODELLING

CONTEXTUALMODELLING

Page 18: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

components

▸ big data processing system: quantifying features from raw data

▸ outlier detection system: learning a descriptive model using features from unsupervised learning process

▸ feedback mechanism and continuous learning: incorporating analyst input

Page 19: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

data characteristics

Page 20: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

data characteristics0.1 data sources

▸ common sources: networking devices and applications log

▸ router, switch, firewall, ids, ips, and load balancer devices

▸ web, database, and micro services

▸ frontend and backend applications

▸ delivered in realtime from widely distributed systems

Page 21: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

data characteristics0.2 data dimensions and unique entities

▸ volume of raw data: metrics (GB/TB) or number of lines (≥ tens of millions on a daily basis)

▸ specific to behavioural analytics: IP addresses, users, sessions, etc.

01010101010101001111010111010101010100011000100101000100111101101010010001001001001000101011110110100111101101001100011110101011101011100110101110110111011001111110000010100110001000001110110101100001000000011010111110111011001110011100010001000100111001000011101111101111011010010010011010001010001110111110001001001001

Page 22: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

data characteristics0.3 malicious activity prevalence

▸ under normal circumstances, malicious activities are extremely rare (generally ≤ 0.1%)

▸ resulting extreme class imbalance in supervised learning

▸ increasing the difficulty of detection processes

▸ unknown and/or unreported attacks introduce noise into data

▸ attack vectors can take a wide variety of shapes

Page 23: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

big data analytics

DAILYWEEKLY

MONTHLY

RAW DATA AGGREGATED DATA

JIM ✖ ✖ ✖

FEATURES

IS NE

W U

SER?

LAST

CHAN

GED

PASS

WOR

D

LAST

IP AD

DRES

S

LAST

SESS

ION

LENG

TH .....

.....

.....

.....

.....

NUM

BER O

F FAI

LED

LOGI

N

JIM

Page 24: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

big data analytics0.1 behavioural signatures

▸ quantifying signatures (often comprises the series of attack steps) from raw data

▸ quantitative values can be defined by security analysts

▸ extracting features per-entity and per-time-segment basis

Page 25: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

big data analytics0.2 design requirements

▸ capable of analysing ≥ 10 millions entities in daily basis

▸ capable of updating and retrieving signatures of active entities, on demand and/or in realtime

Page 26: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

big data analytics0.3.1 process: activity tracking

▸ absorbing the log stream: identifying the entities and updating corresponding records

▸ in short temporal window: 30 minutes, 1 hour, 12 hours, or 24 hours.

▸ focus on efficient retrieval for feature computation

Page 27: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

big data analytics0.3.2 process: activity aggregation

▸ computing behavioural features over an interval of time

▸ retrieving all activity records within given interval

▸ aggregating smaller time unit (minutes, hours, days, weeks) as the feature demands

Page 28: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

algorithm selection

Page 29: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

algorithm selection

Page 30: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

outlier detection

OUTLIER

Page 31: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

outlier detection

▸ matrix decomposition-based outlier analysis

▸ replicator neural networks

▸ density-based outlier analysis

▸ score interpretation

▸ transforming score to probabilities

▸ detection ensembles

MATRIX DECOMPOSITION

REPLICATOR NEURAL NETWORKS

Page 32: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

continuous learning

▸ overcomes limited analyst bandwidth

▸ overcomes weaknesses of unsupervised learning

▸ actively adapts and synthesises new models

PREDICTACT

TRAIN

Page 33: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

example: open network insightleveraging insights from flow and packet analysis

Page 34: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

example: open network insightadvantages

Page 35: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

example: open network insighthow it works

Page 36: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

example: entradanetwork data analytics platform

Page 37: Jim Geovedi - Machine Learning for Cybersecurity

GVDJ #IDSECCONF2016

summary

▸ current problems of security

▸ automatisation of attacks

▸ massive amount of novel malicious code

▸ defences involving manual actions (often ineffective)

▸ machine learning in security

▸ adaptive defences using learning algorithms

▸ automatic detection and analysis of threats

Page 38: Jim Geovedi - Machine Learning for Cybersecurity

QUESTIONS?