SlideShare uma empresa Scribd logo
1 de 48
detecting temporal sybil attacks
       n. lathia, s. hailes & l. capra
      mobisys seminar, sept. 29 2009
the web is based on cooperation...
the web is crowd-sourced...

ratings: recommender, retrieval systems
       captchas: digitising text
     wikis: knowledge repositories
crowd-sourcing is cooperation...

      my ratings compute your recommendations.
           your reviews inform my decisions.
your links help search engines to respond to my queries.
cooperation is policed by reputation and trust

         ebay: online trade and markets
         #followfriday on twitter ? trust
           ratings, ratings, ratings...
...we cooperate without knowing each other

        people are (nearly) anonymous
        why could this be a problem?
for example, recommender systems:

  recommendations → people → rate items →
classification algorithms → recommendations →
                     people...
problem with anonymity:

  recommendations → people → rate items →
classification algorithms → recommendations →
                     people...


can you trust them? are they real people?
        are they rating honestly?
sybil attacks:

   ...when an attacker tries to subvert the system by
    creating a large number of sybils—pseudonymous
identities—in order to gain a disproportionate amount of
                       influence...
sybil attacks: why? how?

random: inject noise, ruin the party for everyone
targetted: promote/demote items. make money?


        APIs: rate content automatically.
recommender system sybil attack:
    shilling, profile injection, ...




          “honest” ratings


          attacker's ratings
each sybil rates:
           target, selected, filler items


target: item that attacker wants promoted/demoted
 selected: similar items, to deceive the algorithm
      filler: other items, to deceive humans
how to defend a recommender system?
a) treat it as a classification problem
         where are the sybils?




           “honest” ratings


           attacker's ratings
problems with classification approach:
    when is your system under attack?


         when to run classifier?
problems with classification approach:
when are sybils damaging your recommendations?




        wait until they have all rated?
proposal:
b) monitor recommender system over time
contributions:
 1. force sybils to draw out their attack
   2. learn normal temporal behaviour
   3. monitor for wide range of attacks
4. force sybils to attack more intelligently
1. force sybils to draw out their attack
 rather than appear, rate, disappear
       how? distrust newcomers
distrust newcomers




prediction shift




                        → time →
distrust newcomers




prediction shift




                        → time →
distrust newcomers




prediction shift




                        → time →
1. force sybils to draw out their attack
         how? distrust newcomers
sybils are forced to appear more than once
examining temporal attack behaviour
  single sybil – – – – group of sybils

  target,                target,
   filler,                filler,
 selected               selected,
                        but also:
group size and dynamics




how many
  sybils?




                      how many ratings per sybil?
how can they behave?



                 (many, few)     (many, many)
how many
  sybils?
                 (few, few)       (few, many)




                     how many ratings per sybil?
how can does this affect the data?
       impact = how much malicious data




how many
  sybils?




                     how many ratings per sybil?
how to measure attacks?
                 precision, recall, impact




         tp                   tp              #sybil ratings
pr =                 re =             imp =
       tp + fp              tp + fn             #ratings
how to detect these attacks? monitor!




            item-level system-level
how many
  sybils?


                        user-level




                      how many ratings per sybil?
how to detect these attacks? monitor!




                   system-level
how many
  sybils?




                   how many ratings per sybil?
overview of the methodology


1. monitor: look at how data changes over time
2. flag: look at how data changes under attack
1. system level
1. system level - attack
(system) avg ratings per user


    1. monitor: exp. weighted moving avg.

        mut = (β mut-|w|) + ((1-β) Rt/Ut)

2. flag: incoming ratings above moving threshold

              Rt/Ut > mut + (αg σt)


      (parameters α, β updated automatically)
1. system level - evaluation
simulated data: play with data variance, attack
                  amplitude
1. system level - evaluation
simulated data: play with data variance, attack
                  amplitude
1. system level - evaluation
real data: netflix ratings (+ timestamps)
1. system level - evaluation
real data: netflix ratings (+ timestamps)
item-level system-level
how many
  sybils?


                        user-level




                      how many ratings per sybil?
(user-level) similar monitor/flag solution

                                                                                                                     1. monitor:
      a. how many high-volume raters?
   b. how much do high-volume raters rate?

2. flag: group size-ratings above threshold
       file:///C:/Documents%20and%20Settings/User/Desktop/misc/documents/19%20attacks/wsdm_2010/img/highVolume.jpg         file:///C:/Documents%20and%20Settings/User/Desktop/misc/documents/19%20attacks/wsdm_2010/img/highRatings.jpg
(user-level) evaluation: real data




how many
  sybils?




                    how many ratings per sybil?
(user-level) evaluation: real data




how many
  sybils?




                    how many ratings per sybil?
(user-level) evaluation: real data




             item-level system-level
how many
  sybils?


                         user-level




                       how many ratings per sybil?
(item-level) slightly different context

        1. the item is rated by many users
           define many? using how other items were rated

    2. the item is rated with extreme ratings
              define extreme? what is avg item mean?

  3. (from a + b) the item mean ratings shifts
                         nuke or promote?



    flag: if all three conditions broken. Why?
1 → popular item. 2 → few extreme ratings. 3 → cold start item
       1 + 2 but not 3 → attack doesn't change anything
3. evaluate: simulated attacks on real data
what next? attackers can defeat these defenses
              the ramp-up attack
but...
conclusions:
 1. force sybils to draw out their attack
   2. learn normal temporal behaviour
     3. monitor system, users, items
4. force sybils to attack more intelligently

Mais conteúdo relacionado

Semelhante a Sybil Attacks - MobiSys Seminar

Profile injection attack detection in recommender system
Profile injection attack detection in recommender systemProfile injection attack detection in recommender system
Profile injection attack detection in recommender systemASHISH PANNU
 
The security mindset securing social media integrations and social learning...
The security mindset   securing social media integrations and social learning...The security mindset   securing social media integrations and social learning...
The security mindset securing social media integrations and social learning...franco_bb
 
DevSecCon Singapore 2018 - Measuring and maximizing vuln discovery efforts by...
DevSecCon Singapore 2018 - Measuring and maximizing vuln discovery efforts by...DevSecCon Singapore 2018 - Measuring and maximizing vuln discovery efforts by...
DevSecCon Singapore 2018 - Measuring and maximizing vuln discovery efforts by...DevSecCon
 
Reading Group Presentation: The Power of Procrastination
Reading Group Presentation: The Power of ProcrastinationReading Group Presentation: The Power of Procrastination
Reading Group Presentation: The Power of ProcrastinationMichael Rushanan
 
Subverting Machine Learning Detections for fun and profit
Subverting Machine Learning Detections for fun and profitSubverting Machine Learning Detections for fun and profit
Subverting Machine Learning Detections for fun and profitRam Shankar Siva Kumar
 
Building a Modern Security Engineering Organization. Zane Lackey
 Building a Modern Security Engineering Organization. Zane Lackey Building a Modern Security Engineering Organization. Zane Lackey
Building a Modern Security Engineering Organization. Zane LackeyYandex
 
Cyber_Attack_Forecasting_Jones_2015
Cyber_Attack_Forecasting_Jones_2015Cyber_Attack_Forecasting_Jones_2015
Cyber_Attack_Forecasting_Jones_2015Malachi Jones
 
Building a Modern Security Engineering Organization
Building a Modern Security Engineering OrganizationBuilding a Modern Security Engineering Organization
Building a Modern Security Engineering OrganizationZane Lackey
 
The Diamond Model for Intrusion Analysis - Threat Intelligence
The Diamond Model for Intrusion Analysis - Threat IntelligenceThe Diamond Model for Intrusion Analysis - Threat Intelligence
The Diamond Model for Intrusion Analysis - Threat IntelligenceThreatConnect
 
Threat Intelligence Baseada em Dados: Métricas de Disseminação e Compartilham...
Threat Intelligence Baseada em Dados: Métricas de Disseminação e Compartilham...Threat Intelligence Baseada em Dados: Métricas de Disseminação e Compartilham...
Threat Intelligence Baseada em Dados: Métricas de Disseminação e Compartilham...Alexandre Sieira
 
DefCamp - Mohamed Bedewi - Building a Weaponized Honeypot
DefCamp - Mohamed Bedewi - Building a Weaponized HoneypotDefCamp - Mohamed Bedewi - Building a Weaponized Honeypot
DefCamp - Mohamed Bedewi - Building a Weaponized HoneypotShah Sheikh
 
Enabling effective hunt teaming and incident response
Enabling effective hunt teaming and incident responseEnabling effective hunt teaming and incident response
Enabling effective hunt teaming and incident responsejeffmcjunkin
 
20101017 program analysis_for_security_livshits_lecture03_security
20101017 program analysis_for_security_livshits_lecture03_security20101017 program analysis_for_security_livshits_lecture03_security
20101017 program analysis_for_security_livshits_lecture03_securityComputer Science Club
 
usenix_2014.pptx
usenix_2014.pptxusenix_2014.pptx
usenix_2014.pptxXyLyu
 
Now you see me, now you don't: chasing evasive malware - Giovanni Vigna
Now you see me, now you don't: chasing evasive malware - Giovanni Vigna Now you see me, now you don't: chasing evasive malware - Giovanni Vigna
Now you see me, now you don't: chasing evasive malware - Giovanni Vigna Lastline, Inc.
 
Profile Injection Attack Detection in Recommender System
Profile Injection Attack Detection in Recommender SystemProfile Injection Attack Detection in Recommender System
Profile Injection Attack Detection in Recommender SystemASHISH PANNU
 

Semelhante a Sybil Attacks - MobiSys Seminar (20)

Profile injection attack detection in recommender system
Profile injection attack detection in recommender systemProfile injection attack detection in recommender system
Profile injection attack detection in recommender system
 
The security mindset securing social media integrations and social learning...
The security mindset   securing social media integrations and social learning...The security mindset   securing social media integrations and social learning...
The security mindset securing social media integrations and social learning...
 
DevSecCon Singapore 2018 - Measuring and maximizing vuln discovery efforts by...
DevSecCon Singapore 2018 - Measuring and maximizing vuln discovery efforts by...DevSecCon Singapore 2018 - Measuring and maximizing vuln discovery efforts by...
DevSecCon Singapore 2018 - Measuring and maximizing vuln discovery efforts by...
 
Reading Group Presentation: The Power of Procrastination
Reading Group Presentation: The Power of ProcrastinationReading Group Presentation: The Power of Procrastination
Reading Group Presentation: The Power of Procrastination
 
Subverting Machine Learning Detections for fun and profit
Subverting Machine Learning Detections for fun and profitSubverting Machine Learning Detections for fun and profit
Subverting Machine Learning Detections for fun and profit
 
Building a Modern Security Engineering Organization. Zane Lackey
 Building a Modern Security Engineering Organization. Zane Lackey Building a Modern Security Engineering Organization. Zane Lackey
Building a Modern Security Engineering Organization. Zane Lackey
 
Cyber_Attack_Forecasting_Jones_2015
Cyber_Attack_Forecasting_Jones_2015Cyber_Attack_Forecasting_Jones_2015
Cyber_Attack_Forecasting_Jones_2015
 
Building a Modern Security Engineering Organization
Building a Modern Security Engineering OrganizationBuilding a Modern Security Engineering Organization
Building a Modern Security Engineering Organization
 
The Diamond Model for Intrusion Analysis - Threat Intelligence
The Diamond Model for Intrusion Analysis - Threat IntelligenceThe Diamond Model for Intrusion Analysis - Threat Intelligence
The Diamond Model for Intrusion Analysis - Threat Intelligence
 
Threat Intelligence Baseada em Dados: Métricas de Disseminação e Compartilham...
Threat Intelligence Baseada em Dados: Métricas de Disseminação e Compartilham...Threat Intelligence Baseada em Dados: Métricas de Disseminação e Compartilham...
Threat Intelligence Baseada em Dados: Métricas de Disseminação e Compartilham...
 
DefCamp - Mohamed Bedewi - Building a Weaponized Honeypot
DefCamp - Mohamed Bedewi - Building a Weaponized HoneypotDefCamp - Mohamed Bedewi - Building a Weaponized Honeypot
DefCamp - Mohamed Bedewi - Building a Weaponized Honeypot
 
Enabling effective hunt teaming and incident response
Enabling effective hunt teaming and incident responseEnabling effective hunt teaming and incident response
Enabling effective hunt teaming and incident response
 
R af d
R af dR af d
R af d
 
Risk Analysis for Dummies
Risk Analysis for DummiesRisk Analysis for Dummies
Risk Analysis for Dummies
 
Major
MajorMajor
Major
 
20101017 program analysis_for_security_livshits_lecture03_security
20101017 program analysis_for_security_livshits_lecture03_security20101017 program analysis_for_security_livshits_lecture03_security
20101017 program analysis_for_security_livshits_lecture03_security
 
usenix_2014.pptx
usenix_2014.pptxusenix_2014.pptx
usenix_2014.pptx
 
Sexy defense
Sexy defenseSexy defense
Sexy defense
 
Now you see me, now you don't: chasing evasive malware - Giovanni Vigna
Now you see me, now you don't: chasing evasive malware - Giovanni Vigna Now you see me, now you don't: chasing evasive malware - Giovanni Vigna
Now you see me, now you don't: chasing evasive malware - Giovanni Vigna
 
Profile Injection Attack Detection in Recommender System
Profile Injection Attack Detection in Recommender SystemProfile Injection Attack Detection in Recommender System
Profile Injection Attack Detection in Recommender System
 

Mais de Neal Lathia

Everything around the NLP (London.AI Feb 2021)
Everything around the NLP (London.AI Feb 2021)Everything around the NLP (London.AI Feb 2021)
Everything around the NLP (London.AI Feb 2021)Neal Lathia
 
Using machine learning for customer service (Data Talks Club)
Using machine learning for customer service (Data Talks Club)Using machine learning for customer service (Data Talks Club)
Using machine learning for customer service (Data Talks Club)Neal Lathia
 
Using language models to supercharge Monzo’s customer support
 Using language models to supercharge Monzo’s customer support Using language models to supercharge Monzo’s customer support
Using language models to supercharge Monzo’s customer supportNeal Lathia
 
Making Better Decisions Faster
Making Better Decisions FasterMaking Better Decisions Faster
Making Better Decisions FasterNeal Lathia
 
Machine Learning, Faster
Machine Learning, FasterMachine Learning, Faster
Machine Learning, FasterNeal Lathia
 
AI & Personalised Experiences
AI & Personalised ExperiencesAI & Personalised Experiences
AI & Personalised ExperiencesNeal Lathia
 
Opportunities & Challenges in Personalised Travel
Opportunities & Challenges in Personalised TravelOpportunities & Challenges in Personalised Travel
Opportunities & Challenges in Personalised TravelNeal Lathia
 
Bootstrapping a Destination Recommendation Engine
Bootstrapping a Destination Recommendation EngineBootstrapping a Destination Recommendation Engine
Bootstrapping a Destination Recommendation EngineNeal Lathia
 
Machine Learning for Product Managers
Machine Learning for Product ManagersMachine Learning for Product Managers
Machine Learning for Product ManagersNeal Lathia
 
Mining Smartphone Data (with Python)
Mining Smartphone Data (with Python)Mining Smartphone Data (with Python)
Mining Smartphone Data (with Python)Neal Lathia
 
Happier and Healthier with Smartphone Data
Happier and Healthier with Smartphone DataHappier and Healthier with Smartphone Data
Happier and Healthier with Smartphone DataNeal Lathia
 
Data Science in Digital Health
Data Science in Digital HealthData Science in Digital Health
Data Science in Digital HealthNeal Lathia
 
Using Smartphones to Measure (and Intervene in) Daily Life
Using Smartphones to Measure (and Intervene in) Daily LifeUsing Smartphones to Measure (and Intervene in) Daily Life
Using Smartphones to Measure (and Intervene in) Daily LifeNeal Lathia
 
Analysing Daily Behaviours with Large-Scale Smartphone Data
Analysing Daily Behaviours with Large-Scale Smartphone DataAnalysing Daily Behaviours with Large-Scale Smartphone Data
Analysing Daily Behaviours with Large-Scale Smartphone DataNeal Lathia
 
Cambridge Quantified Self Meetup
Cambridge Quantified Self MeetupCambridge Quantified Self Meetup
Cambridge Quantified Self MeetupNeal Lathia
 
Data Science in #mHealth
Data Science in #mHealthData Science in #mHealth
Data Science in #mHealthNeal Lathia
 
Tube Star: Crowd-Sourced Experiences on Public Transport
Tube Star: Crowd-Sourced Experiences on Public Transport Tube Star: Crowd-Sourced Experiences on Public Transport
Tube Star: Crowd-Sourced Experiences on Public Transport Neal Lathia
 
Emotion Sense: From Design to Deployment
Emotion Sense: From Design to DeploymentEmotion Sense: From Design to Deployment
Emotion Sense: From Design to DeploymentNeal Lathia
 
Opportunities and Challenges of Using Smartphones for Health Monitoring and I...
Opportunities and Challenges of Using Smartphones for Health Monitoring and I...Opportunities and Challenges of Using Smartphones for Health Monitoring and I...
Opportunities and Challenges of Using Smartphones for Health Monitoring and I...Neal Lathia
 
Using Smartphones to Research Daily Life
Using Smartphones to Research Daily LifeUsing Smartphones to Research Daily Life
Using Smartphones to Research Daily LifeNeal Lathia
 

Mais de Neal Lathia (20)

Everything around the NLP (London.AI Feb 2021)
Everything around the NLP (London.AI Feb 2021)Everything around the NLP (London.AI Feb 2021)
Everything around the NLP (London.AI Feb 2021)
 
Using machine learning for customer service (Data Talks Club)
Using machine learning for customer service (Data Talks Club)Using machine learning for customer service (Data Talks Club)
Using machine learning for customer service (Data Talks Club)
 
Using language models to supercharge Monzo’s customer support
 Using language models to supercharge Monzo’s customer support Using language models to supercharge Monzo’s customer support
Using language models to supercharge Monzo’s customer support
 
Making Better Decisions Faster
Making Better Decisions FasterMaking Better Decisions Faster
Making Better Decisions Faster
 
Machine Learning, Faster
Machine Learning, FasterMachine Learning, Faster
Machine Learning, Faster
 
AI & Personalised Experiences
AI & Personalised ExperiencesAI & Personalised Experiences
AI & Personalised Experiences
 
Opportunities & Challenges in Personalised Travel
Opportunities & Challenges in Personalised TravelOpportunities & Challenges in Personalised Travel
Opportunities & Challenges in Personalised Travel
 
Bootstrapping a Destination Recommendation Engine
Bootstrapping a Destination Recommendation EngineBootstrapping a Destination Recommendation Engine
Bootstrapping a Destination Recommendation Engine
 
Machine Learning for Product Managers
Machine Learning for Product ManagersMachine Learning for Product Managers
Machine Learning for Product Managers
 
Mining Smartphone Data (with Python)
Mining Smartphone Data (with Python)Mining Smartphone Data (with Python)
Mining Smartphone Data (with Python)
 
Happier and Healthier with Smartphone Data
Happier and Healthier with Smartphone DataHappier and Healthier with Smartphone Data
Happier and Healthier with Smartphone Data
 
Data Science in Digital Health
Data Science in Digital HealthData Science in Digital Health
Data Science in Digital Health
 
Using Smartphones to Measure (and Intervene in) Daily Life
Using Smartphones to Measure (and Intervene in) Daily LifeUsing Smartphones to Measure (and Intervene in) Daily Life
Using Smartphones to Measure (and Intervene in) Daily Life
 
Analysing Daily Behaviours with Large-Scale Smartphone Data
Analysing Daily Behaviours with Large-Scale Smartphone DataAnalysing Daily Behaviours with Large-Scale Smartphone Data
Analysing Daily Behaviours with Large-Scale Smartphone Data
 
Cambridge Quantified Self Meetup
Cambridge Quantified Self MeetupCambridge Quantified Self Meetup
Cambridge Quantified Self Meetup
 
Data Science in #mHealth
Data Science in #mHealthData Science in #mHealth
Data Science in #mHealth
 
Tube Star: Crowd-Sourced Experiences on Public Transport
Tube Star: Crowd-Sourced Experiences on Public Transport Tube Star: Crowd-Sourced Experiences on Public Transport
Tube Star: Crowd-Sourced Experiences on Public Transport
 
Emotion Sense: From Design to Deployment
Emotion Sense: From Design to DeploymentEmotion Sense: From Design to Deployment
Emotion Sense: From Design to Deployment
 
Opportunities and Challenges of Using Smartphones for Health Monitoring and I...
Opportunities and Challenges of Using Smartphones for Health Monitoring and I...Opportunities and Challenges of Using Smartphones for Health Monitoring and I...
Opportunities and Challenges of Using Smartphones for Health Monitoring and I...
 
Using Smartphones to Research Daily Life
Using Smartphones to Research Daily LifeUsing Smartphones to Research Daily Life
Using Smartphones to Research Daily Life
 

Último

Sociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning ExhibitSociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning Exhibitjbellavia9
 
Food safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdfFood safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdfSherif Taha
 
General Principles of Intellectual Property: Concepts of Intellectual Proper...
General Principles of Intellectual Property: Concepts of Intellectual  Proper...General Principles of Intellectual Property: Concepts of Intellectual  Proper...
General Principles of Intellectual Property: Concepts of Intellectual Proper...Poonam Aher Patil
 
Jamworks pilot and AI at Jisc (20/03/2024)
Jamworks pilot and AI at Jisc (20/03/2024)Jamworks pilot and AI at Jisc (20/03/2024)
Jamworks pilot and AI at Jisc (20/03/2024)Jisc
 
Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)Jisc
 
How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17Celine George
 
ICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxAreebaZafar22
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsTechSoup
 
How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17Celine George
 
Wellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptxWellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptxJisc
 
How to setup Pycharm environment for Odoo 17.pptx
How to setup Pycharm environment for Odoo 17.pptxHow to setup Pycharm environment for Odoo 17.pptx
How to setup Pycharm environment for Odoo 17.pptxCeline George
 
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptxHMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptxEsquimalt MFRC
 
How to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POSHow to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POSCeline George
 
Single or Multiple melodic lines structure
Single or Multiple melodic lines structureSingle or Multiple melodic lines structure
Single or Multiple melodic lines structuredhanjurrannsibayan2
 
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptx
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptxHMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptx
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptxmarlenawright1
 
Interdisciplinary_Insights_Data_Collection_Methods.pptx
Interdisciplinary_Insights_Data_Collection_Methods.pptxInterdisciplinary_Insights_Data_Collection_Methods.pptx
Interdisciplinary_Insights_Data_Collection_Methods.pptxPooja Bhuva
 
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdf
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdfUnit 3 Emotional Intelligence and Spiritual Intelligence.pdf
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdfDr Vijay Vishwakarma
 
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...pradhanghanshyam7136
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfAdmir Softic
 

Último (20)

Sociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning ExhibitSociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning Exhibit
 
Food safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdfFood safety_Challenges food safety laboratories_.pdf
Food safety_Challenges food safety laboratories_.pdf
 
General Principles of Intellectual Property: Concepts of Intellectual Proper...
General Principles of Intellectual Property: Concepts of Intellectual  Proper...General Principles of Intellectual Property: Concepts of Intellectual  Proper...
General Principles of Intellectual Property: Concepts of Intellectual Proper...
 
Jamworks pilot and AI at Jisc (20/03/2024)
Jamworks pilot and AI at Jisc (20/03/2024)Jamworks pilot and AI at Jisc (20/03/2024)
Jamworks pilot and AI at Jisc (20/03/2024)
 
Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)Accessible Digital Futures project (20/03/2024)
Accessible Digital Futures project (20/03/2024)
 
How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17How to Give a Domain for a Field in Odoo 17
How to Give a Domain for a Field in Odoo 17
 
ICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptx
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The Basics
 
How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17How to Create and Manage Wizard in Odoo 17
How to Create and Manage Wizard in Odoo 17
 
Wellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptxWellbeing inclusion and digital dystopias.pptx
Wellbeing inclusion and digital dystopias.pptx
 
How to setup Pycharm environment for Odoo 17.pptx
How to setup Pycharm environment for Odoo 17.pptxHow to setup Pycharm environment for Odoo 17.pptx
How to setup Pycharm environment for Odoo 17.pptx
 
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptxHMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
HMCS Max Bernays Pre-Deployment Brief (May 2024).pptx
 
How to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POSHow to Manage Global Discount in Odoo 17 POS
How to Manage Global Discount in Odoo 17 POS
 
Single or Multiple melodic lines structure
Single or Multiple melodic lines structureSingle or Multiple melodic lines structure
Single or Multiple melodic lines structure
 
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptx
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptxHMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptx
HMCS Vancouver Pre-Deployment Brief - May 2024 (Web Version).pptx
 
Interdisciplinary_Insights_Data_Collection_Methods.pptx
Interdisciplinary_Insights_Data_Collection_Methods.pptxInterdisciplinary_Insights_Data_Collection_Methods.pptx
Interdisciplinary_Insights_Data_Collection_Methods.pptx
 
Spatium Project Simulation student brief
Spatium Project Simulation student briefSpatium Project Simulation student brief
Spatium Project Simulation student brief
 
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdf
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdfUnit 3 Emotional Intelligence and Spiritual Intelligence.pdf
Unit 3 Emotional Intelligence and Spiritual Intelligence.pdf
 
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...Kodo Millet  PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdf
 

Sybil Attacks - MobiSys Seminar

  • 1. detecting temporal sybil attacks n. lathia, s. hailes & l. capra mobisys seminar, sept. 29 2009
  • 2. the web is based on cooperation...
  • 3. the web is crowd-sourced... ratings: recommender, retrieval systems captchas: digitising text wikis: knowledge repositories
  • 4. crowd-sourcing is cooperation... my ratings compute your recommendations. your reviews inform my decisions. your links help search engines to respond to my queries.
  • 5. cooperation is policed by reputation and trust ebay: online trade and markets #followfriday on twitter ? trust ratings, ratings, ratings...
  • 6. ...we cooperate without knowing each other people are (nearly) anonymous why could this be a problem?
  • 7. for example, recommender systems: recommendations → people → rate items → classification algorithms → recommendations → people...
  • 8. problem with anonymity: recommendations → people → rate items → classification algorithms → recommendations → people... can you trust them? are they real people? are they rating honestly?
  • 9. sybil attacks: ...when an attacker tries to subvert the system by creating a large number of sybils—pseudonymous identities—in order to gain a disproportionate amount of influence...
  • 10. sybil attacks: why? how? random: inject noise, ruin the party for everyone targetted: promote/demote items. make money? APIs: rate content automatically.
  • 11. recommender system sybil attack: shilling, profile injection, ... “honest” ratings attacker's ratings
  • 12. each sybil rates: target, selected, filler items target: item that attacker wants promoted/demoted selected: similar items, to deceive the algorithm filler: other items, to deceive humans
  • 13. how to defend a recommender system?
  • 14. a) treat it as a classification problem where are the sybils? “honest” ratings attacker's ratings
  • 15. problems with classification approach: when is your system under attack? when to run classifier?
  • 16. problems with classification approach: when are sybils damaging your recommendations? wait until they have all rated?
  • 18. contributions: 1. force sybils to draw out their attack 2. learn normal temporal behaviour 3. monitor for wide range of attacks 4. force sybils to attack more intelligently
  • 19. 1. force sybils to draw out their attack rather than appear, rate, disappear how? distrust newcomers
  • 23. 1. force sybils to draw out their attack how? distrust newcomers sybils are forced to appear more than once
  • 24. examining temporal attack behaviour single sybil – – – – group of sybils target, target, filler, filler, selected selected, but also:
  • 25. group size and dynamics how many sybils? how many ratings per sybil?
  • 26. how can they behave? (many, few) (many, many) how many sybils? (few, few) (few, many) how many ratings per sybil?
  • 27. how can does this affect the data? impact = how much malicious data how many sybils? how many ratings per sybil?
  • 28. how to measure attacks? precision, recall, impact tp tp #sybil ratings pr = re = imp = tp + fp tp + fn #ratings
  • 29. how to detect these attacks? monitor! item-level system-level how many sybils? user-level how many ratings per sybil?
  • 30. how to detect these attacks? monitor! system-level how many sybils? how many ratings per sybil?
  • 31. overview of the methodology 1. monitor: look at how data changes over time 2. flag: look at how data changes under attack
  • 33. 1. system level - attack
  • 34. (system) avg ratings per user 1. monitor: exp. weighted moving avg. mut = (β mut-|w|) + ((1-β) Rt/Ut) 2. flag: incoming ratings above moving threshold Rt/Ut > mut + (αg σt) (parameters α, β updated automatically)
  • 35. 1. system level - evaluation simulated data: play with data variance, attack amplitude
  • 36. 1. system level - evaluation simulated data: play with data variance, attack amplitude
  • 37. 1. system level - evaluation real data: netflix ratings (+ timestamps)
  • 38. 1. system level - evaluation real data: netflix ratings (+ timestamps)
  • 39. item-level system-level how many sybils? user-level how many ratings per sybil?
  • 40. (user-level) similar monitor/flag solution 1. monitor: a. how many high-volume raters? b. how much do high-volume raters rate? 2. flag: group size-ratings above threshold file:///C:/Documents%20and%20Settings/User/Desktop/misc/documents/19%20attacks/wsdm_2010/img/highVolume.jpg file:///C:/Documents%20and%20Settings/User/Desktop/misc/documents/19%20attacks/wsdm_2010/img/highRatings.jpg
  • 41. (user-level) evaluation: real data how many sybils? how many ratings per sybil?
  • 42. (user-level) evaluation: real data how many sybils? how many ratings per sybil?
  • 43. (user-level) evaluation: real data item-level system-level how many sybils? user-level how many ratings per sybil?
  • 44. (item-level) slightly different context 1. the item is rated by many users define many? using how other items were rated 2. the item is rated with extreme ratings define extreme? what is avg item mean? 3. (from a + b) the item mean ratings shifts nuke or promote? flag: if all three conditions broken. Why? 1 → popular item. 2 → few extreme ratings. 3 → cold start item 1 + 2 but not 3 → attack doesn't change anything
  • 45. 3. evaluate: simulated attacks on real data
  • 46. what next? attackers can defeat these defenses the ramp-up attack
  • 48. conclusions: 1. force sybils to draw out their attack 2. learn normal temporal behaviour 3. monitor system, users, items 4. force sybils to attack more intelligently