This document proposes monitoring recommender systems over time to detect sybil attacks. It suggests distrusting newcomers to force sybils to draw out their attacks. It recommends monitoring at the system, user, and item levels by learning normal temporal behavior and flagging anomalies. The key contributions are forcing sybils to reveal attacks through prolonged activity and monitoring a wide range of attacks over time.
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.
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
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
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
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
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