Privacy Against Brute-Force Inference Attacks

Osia, Seyed Ali; Rassouli, Borzoo; Haddadi, Hamed; Rabiee, Hamid R.; Gündüz, Deniz

doi:10.1109/isit.2019.8849291

Cited by 12 publications

(13 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1) Considering the case when the adversary is inferring an attribute U of X, we propose the non-stochastic brute-force guessing leakage as the ratio of the worst-case number of guesses for the adversary in the presence of the output Y and in the absence of it. This definition is consistent with the stochastic brute-force guessing leakage [17] with the exception of avoiding distributions or statistics.…”

Section: Introductionsupporting

confidence: 68%

Measuring Information Leakage in Non-stochastic Brute-Force Guessing

Ding¹,

Farokhi²

2021

Preprint

View full text Add to dashboard Cite

This paper proposes an operational measure of nonstochastic information leakage to formalize privacy against a brute-force guessing adversary. The information is measured by non-probabilistic uncertainty of uncertain variables, the nonstochastic counterparts of random variables. For X that is related to released data Y , the non-stochastic brute-force leakage is measured by the complexity of exhaustively checking all the possibilities of the private attribute U of X by an adversary. The complexity refers to the number of trials to successfully guess U . Maximizing this leakage over all possible private attributes U gives rise to the maximal (i.e., worst-case) nonstochastic brute-force guessing leakage. This is proved to be fully determined by the minimal non-stochastic uncertainty of X given Y , which also determines the worst-case attribute U indicating the highest privacy risk if Y is disclosed. The maximal non-stochastic brute-force guessing leakage is shown to be proportional to the non-stochastic identifiability of X given Y and upper bounds the existing maximin information. The latter quantifies the information leakage when an adversary must perfectly guess U in one-shot via Y . Experiments are used to demonstrate the tradeoff between the maximal non-stochastic brute-force guessing leakage and the data utility (measured by the maximum quantization error) and to illustrate the relationship between maximin information and stochastic one-shot maximal leakage.

show abstract

Section: Introductionsupporting

confidence: 68%

Measuring Information Leakage in Non-stochastic Brute-Force Guessing

Ding¹,

Farokhi²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Finally, hypothesis testing has been used to propose more general definitions of privacy, such as identifiability [129, 130]. Non‐binary hypothesis testing and guessing has been also recently used to define worst‐case measures of information leakage to define robust privacy measures [81, 131, 132].…”

Section: Smart‐meter Privacy With Demand Shaping and Load Schedulingmentioning

confidence: 99%

Review of results on smart‐meter privacy by data manipulation, demand shaping, and load scheduling

Farokhi

2020

IET Smart Grid

View full text Add to dashboard Cite

“…Privacy is an important concern for the adoption of many IoT services, and there is a growing demand from consumers to keep their personal information private. Privacy has been widely studied in the literature [1][2][3][4][5][6][7][8][9][10], and a vast number of privacy measures have been introduced, including differential privacy [1], mutual information (MI) [2][3][4][5][6][7][8], total variation distance [11], maximal leakage [12,13], and guessing leakage [14], to count a few.…”

Section: Introductionmentioning

confidence: 99%

“…The user's goal is to prevent the secret from being accurately detected by the adversary while the useful data is revealed to the adversary for utility. Differently from the existing works [2,3,11,12,14,15], which typically consider a one-shot data release problem, we consider a discrete time system, and assume that the user can choose from among a finite number of data release mechanisms at each time. These might correspond to different types of sensor readings.…”

Section: Introductionmentioning

confidence: 99%

Active Privacy-Utility Trade-Off Against A Hypothesis Testing Adversary

Erdemir

Dragotti

Gündüz

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

We consider a user releasing her data containing some personal information in return of a service. We model user's personal information as two correlated random variables, one of them, called the secret variable, is to be kept private, while the other, called the useful variable, is to be disclosed for utility. We consider active sequential data release, where at each time step the user chooses from among a finite set of release mechanisms, each revealing some information about the user's personal information, i.e., the true hypotheses, albeit with different statistics. The user manages data release in an online fashion such that maximum amount of information is revealed about the latent useful variable, while the confidence for the sensitive variable is kept below a predefined level. For the utility, we consider both the probability of correct detection of the useful variable and the mutual information (MI) between the useful variable and released data. We formulate both problems as a Markov decision process (MDP), and numerically solve them by advantage actor-critic (A2C) deep reinforcement learning (RL).

show abstract

Privacy Against Brute-Force Inference Attacks

Cited by 12 publications

References 20 publications

Measuring Information Leakage in Non-stochastic Brute-Force Guessing

Measuring Information Leakage in Non-stochastic Brute-Force Guessing

Review of results on smart‐meter privacy by data manipulation, demand shaping, and load scheduling

Active Privacy-Utility Trade-Off Against A Hypothesis Testing Adversary

Contact Info

Product

Resources

About