Robust rs research We assume that the attacker has no direct access to the ratings database manipulation achieved via the creation of false profiles only a We ignore system-level methods(e.g. Captchas)for preventing the generation of false identities or ratings
Tutorial on Robustness of Recommender Systems What is Robustness? Profile Injection Attacks Robust RS Research We assume that the attacker has no direct access to the ratings database – manipulation achieved via the creation of false profiles only. We ignore system-level methods (e.g. Captchas) for preventing the generation of false identities or ratings Focus is on the recommendation algorithm’s ability to resist manipulation either by Identifying false profiles from their statistical properties and ignoring or lessening their impact on the generation of recommendations; or Generating recommendations in a manner that is inherently insensitive to manipulation. RecSys 2011: Tutorial on Recommender Robustness
Robust rs research We assume that the attacker has no direct access to the ratings database manipulation achieved via the creation of false profiles only ■ We ignore system-level methods(e.g. Captchas)for preventing the generation of false identities or ratings a Focus is on the recommendation agorithm s ability to resist manipulation either by
Tutorial on Robustness of Recommender Systems What is Robustness? Profile Injection Attacks Robust RS Research We assume that the attacker has no direct access to the ratings database – manipulation achieved via the creation of false profiles only. We ignore system-level methods (e.g. Captchas) for preventing the generation of false identities or ratings Focus is on the recommendation algorithm’s ability to resist manipulation either by Identifying false profiles from their statistical properties and ignoring or lessening their impact on the generation of recommendations; or Generating recommendations in a manner that is inherently insensitive to manipulation. RecSys 2011: Tutorial on Recommender Robustness
Robust rs research We assume that the attacker has no direct access to the ratings database manipulation achieved via the creation of false profiles only ■ We ignore system-level methods(e.g. Captchas)for preventing the generation of false identities or ratings a Focus is on the recommendation agorithm s ability to resist manipulation either by a Identifying false profiles from their statistical properties and ignoring or lessening their impact on the generation of
Tutorial on Robustness of Recommender Systems What is Robustness? Profile Injection Attacks Robust RS Research We assume that the attacker has no direct access to the ratings database – manipulation achieved via the creation of false profiles only. We ignore system-level methods (e.g. Captchas) for preventing the generation of false identities or ratings Focus is on the recommendation algorithm’s ability to resist manipulation either by Identifying false profiles from their statistical properties and ignoring or lessening their impact on the generation of recommendations; or Generating recommendations in a manner that is inherently insensitive to manipulation. RecSys 2011: Tutorial on Recommender Robustness
Robust rs research We assume that the attacker has no direct access to the ratings database manipulation achieved via the creation of false profiles only ■ We ignore system-level methods(e.g. Captchas)for preventing the generation of false identities or ratings a Focus is on the recommendation agorithm s ability to resist manipulation either by a Identifying false profiles from their statistical properties and ignoring or lessening their impact on the generation of recommendations: or a Generating recommendations in a manner that is inherent sensitive to manipulation
Tutorial on Robustness of Recommender Systems What is Robustness? Profile Injection Attacks Robust RS Research We assume that the attacker has no direct access to the ratings database – manipulation achieved via the creation of false profiles only. We ignore system-level methods (e.g. Captchas) for preventing the generation of false identities or ratings Focus is on the recommendation algorithm’s ability to resist manipulation either by Identifying false profiles from their statistical properties and ignoring or lessening their impact on the generation of recommendations; or Generating recommendations in a manner that is inherently insensitive to manipulation. RecSys 2011: Tutorial on Recommender Robustness
Example User2 User4 Userb
Tutorial on Robustness of Recommender Systems What is Robustness? Profile Injection Attacks Example RecSys 2011: Tutorial on Recommender Robustness