L-diversity: Privacy beyond k-anonymity
Citations
3,314 citations
Additional excerpts
...We then show some interesting applications of these techniques, presenting algorithms for three specific tasks and three general results on differentially private learning....
[...]
3,281 citations
2,700 citations
2,241 citations
Cites background from "L-diversity: Privacy beyond k-anony..."
...This does not guarantee any privacy, because the values of sensitive attributes associated with a given quasi-identifier may not be sufficiently diverse [20, 21] or the adversary may know more than just the quasiidentifiers [20]....
[...]
1,953 citations
References
10,454 citations
"L-diversity: Privacy beyond k-anony..." refers background or methods in this paper
...[1-10], [11-20], etc), we would end up with very large q-blocks....
[...]
...This is called the monotonicity property , and it has been used extensively in frequent itemset mining algorithms [4]....
[...]
...This is called the monotonicity property, and it has been used extensively in frequent itemset mining algorithms [Agrawal and Srikant 1994]. k-anonymity satis.es the monotonicity property, and it is this property which guarantees the correctness of all ef.cient algorithms [Bayardo and Agrawal…...
[...]
...[1-5], [6-10], [11-15], etc) were generalized to age groups of length 10 (i....
[...]
7,925 citations
"L-diversity: Privacy beyond k-anony..." refers background or methods in this paper
...To counter linking attacks using quasi-identi.ers, Samarati and Sweeney proposed a de.nition of privacy called k-anonymity [Samarati 2001; Sweeney 2002]....
[...]
...This “linking attack” managed to uniquely identify the medical records of the governor of Massachusetts in the medical data [24]....
[...]
...Samarati 2001; Sweeney 2002; Zhong et al. 2005], k-anonymity has grown in popularity....
[...]
...Because of its conceptual simplicity, k-anonymity has been widely discussed as a viable definition of privacy in data publishing, and due to algorithmic advances in creatin g k-anonymous versions of a dataset [3, 6, 16, 18, 21, 24, 25], k-anonymity has grown in popularity....
[...]
...has been proposed which guarantees that every individual is hidden in a group of size k with respect to the non-sensitive attributes [24]....
[...]
3,579 citations
3,173 citations
"L-diversity: Privacy beyond k-anony..." refers background in this paper
...[Agrawal and Srikant 2000] propose randomization techniques that can be employed by individuals to mask their sensitive information while allowing the data collector to build good decision trees on the data....
[...]
2,929 citations