A rigorous and customizable framework for privacy

By Daniel Kifer, Ashwin Machanavajjhala. 2012

523 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Sociology and Political Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Sociology and Political Science

Citations in the corpus

Dependence Makes You Vulnberable: Differential Privacy Under Dependent Tuples (2016, methodology): “There exist limited prior work that have outlined realistic inference attacks exposing the vulnerability of DP mechanisms under dependent data tuples [24], [25].”
Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds (2014, background): “See Dwork [18], Kasiviswanathan and Smith [30], Kifer and Machanavajjhala [33] for discussion of the “semantics” of differential privacy.”
Coupled-Worlds Privacy: Exploiting Adversarial Uncertainty in Statistical Data Privacy (2013, methodology): “The inference-based version of our definition provides a more transparent view of the key difference between our approach and that of previous work taking adversarial uncertainty into account [1], [16].”
Profile-based Privacy for Locally Private Computations (2019, methodology): “Our proposed definition is related to two commonly used privacy frameworks: the generalized Pufferfish privacy framework [3], and geoindistinguishability [4].”
Tacit Knowledge in Expert Coaching: Science or Art? (2006, background): “It would seem that it would be easier to defi ne an expert within these fi elds rather than in ill-structured, constantly changing environments where speed is of the essence, e.g., teaching and coaching (Berliner, 1994; Krishna & Morgan, 2002).”
Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Bounds (2014, background): “See [15, 27, 28] for discussion of the “semantics” of differential privacy.”
Cardinality Estimators do not Preserve Privacy (2018, background): “Data-generating probability distributions were considered as a source of uncertainty in [7, 11, 15, 28, 30, 37, 43]; and some deterministic algorithms, which do not add noise, have been shown to preserve privacy under this assumption [7, 11, 28].”
Generating synthetic data in finance: opportunities, challenges and pitfalls (2020, background): “Indeed, even for tabular data differential privacy is not the last word, with future directions suggested by Kifer and Machanavajjhala [58].”
Private Empirical Risk Minimization, Revisited (2014, background): “See Dwork [12], Kasiviswanathan and Smith [26], Kifer and Machanavajjhala [29] for discussion of the " semantics " of differential privacy.”
Privacy and Statistical Risk: Formalisms and Minimax Bounds (2014, background): “It has been quite challenging to give rigorous deﬁnitions of privacy against weaker adversaries (such deﬁnitions have often been shown [13, 12] to have fatal ﬂaws), but subsequent works have broadened our understanding of acceptable privacy deﬁnitions and adversaries [20, 21, 2].”
Protecting Locations with Differential Privacy under Temporal Correlations (2014, background): “does not capture the worst case that is important for a privacy model. Hence, in our paper, we assume a similar strong adversary model but dene a rigorous privacy notion based on dierential privacy [17, 31, 32]. To our knowledge, none of the existing work has provided perturbation mechanisms with di”
On the 'Semantics' of Differential Privacy: A Bayesian Formulation (2008, background): “Kifer and Machanavajjhala [15] use this prior-to-posterior approach to generalize differential privacy to other settings.”