Name:
Anti-discrimination analysis.pdf
Size:
487.8Kb
Format:
PDF
Description:
Accepted Manuscript
Type
Conference PaperKAUST Department
Computer Science ProgramComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Date
2014-09-01Online Publication Date
2014-09-01Print Publication Date
2014Permanent link to this record
http://hdl.handle.net/10754/556651
Metadata
Show full item recordAbstract
Social discrimination discovery from data is an important task to identify illegal and unethical discriminatory patterns towards protected-by-law groups, e.g., ethnic minorities. We deploy privacy attack strategies as tools for discrimination discovery under hard assumptions which have rarely tackled in the literature: indirect discrimination discovery, privacy-aware discrimination discovery, and discrimination data recovery. The intuition comes from the intriguing parallel between the role of the anti-discrimination authority in the three scenarios above and the role of an attacker in private data publishing. We design strategies and algorithms inspired/based on Frèchet bounds attacks, attribute inference attacks, and minimality attacks to the purpose of unveiling hidden discriminatory practices. Experimental results show that they can be effective tools in the hands of anti-discrimination authorities.Citation
Ruggieri, S., Hajian, S., Kamiran, F., & Zhang, X. (2014). Anti-discrimination Analysis Using Privacy Attack Strategies. Lecture Notes in Computer Science, 694–710. doi:10.1007/978-3-662-44851-9_44Publisher
Springer NatureConference/Event name
European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2014Additional Links
http://link.springer.com/chapter/10.1007%2F978-3-662-44851-9_44ae974a485f413a2113503eed53cd6c53
10.1007/978-3-662-44851-9_44