Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userOn Privacy and Confidentiality of Communications in Organizational Graphs
227
0
0.0
(
0
)
Added by
Masoumeh Shafieinejad
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Machine learned models trained on organizational communication data, such as emails in an enterprise, carry unique risks of breaching confidentiality, even if the model is intended only for internal use. This work shows how confidentiality is distinct from privacy in an enterprise context, and aims to formulate an approach to preserving confidentiality while leveraging principles from differential privacy. The goal is to perform machine learning tasks, such as learning a language model or performing topic analysis, using interpersonal communications in the organization, while not learning about confidential information shared in the organization. Works that apply differential privacy techniques to natural language processing tasks usually assume independently distributed data, and overlook potential correlation among the records. Ignoring this correlation results in a fictional promise of privacy. Naively extending differential privacy techniques to focus on group privacy instead of record-level privacy is a straightforward approach to mitigate this issue. This approach, although providing a more realistic privacy-guarantee, is over-cautious and severely impacts model utility. We show this gap between these two extreme measures of privacy over two language tasks, and introduce a middle-ground solution. We propose a model that captures the correlation in the social network graph, and incorporates this correlation in the privacy calculations through Pufferfish privacy principles.
rate research
Read More
Distributed collaborative learning (DCL) paradigms enable building joint machine learning models from distrusting multi-party participants. Data confidentiality is guaranteed by retaining private training data on each participants local infrastructure. However, this approach to achieving data confidentiality makes todays DCL designs fundamentally vulnerable to data poisoning and backdoor attacks. It also limits DCLs model accountability, which is key to backtracking the responsible bad training data instances/contributors. In this paper, we introduce CALTRAIN, a Trusted Execution Environment (TEE) based centralized multi-party collaborative learning system that simultaneously achieves data confidentiality and model accountability. CALTRAIN enforces isolated computation on centrally aggregated training data to guarantee data confidentiality. To support building accountable learning models, we securely maintain the links between training instances and their corresponding contributors. Our evaluation shows that the models generated from CALTRAIN can achieve the same prediction accuracy when compared to the models trained in non-protected environments. We also demonstrate that when malicious training participants tend to implant backdoors during model training, CALTRAIN can accurately and precisely discover the poisoned and mislabeled training data that lead to the runtime mispredictions.
Cryptocurrency off-chain networks such as Lightning (e.g., Bitcoin) or Raiden (e.g., Ethereum) aim to increase the scalability of traditional on-chain transactions. To support nodes in learning about possible paths to route their transactions, these networks need to provide gossip and probing mechanisms. This paper explores whether these mechanisms may be exploited to infer sensitive information about the flow of transactions, and eventually harm privacy. In particular, we identify two threats, related to an active and a passive adversary. The first is a probing attack: here the adversary aims to detect the maximum amount which is transferable in a given direction over a target channel by actively probing it and differentiating the response messages it receives. The second is a timing attack: the adversary discovers how close the destination of a routed payment actually is, by acting as a passive man-in-the middle and analyzing the time deltas between sent messages and their corresponding responses. We then analyze the limitations of these attacks and propose remediations for scenarios in which they are able to produce accurate results.
The calibration of noise for a privacy-preserving mechanism depends on the sensitivity of the query and the prescribed privacy level. A data steward must make the non-trivial choice of a privacy level that balances the requirements of users and the monetary constraints of the business entity. We analyse roles of the sources of randomness, namely the explicit randomness induced by the noise distribution and the implicit randomness induced by the data-generation distribution, that are involved in the design of a privacy-preserving mechanism. The finer analysis enables us to provide stronger privacy guarantees with quantifiable risks. Thus, we propose privacy at risk that is a probabilistic calibration of privacy-preserving mechanisms. We provide a composition theorem that leverages privacy at risk. We instantiate the probabilistic calibration for the Laplace mechanism by providing analytical results. We also propose a cost model that bridges the gap between the privacy level and the compensation budget estimated by a GDPR compliant business entity. The convexity of the proposed cost model leads to a unique fine-tuning of privacy level that minimises the compensation budget. We show its effectiveness by illustrating a realistic scenario that avoids overestimation of the compensation budget by using privacy at risk for the Laplace mechanism. We quantitatively show that composition using the cost optimal privacy at risk provides stronger privacy guarantee than the classical advanced composition.
Social graphs are widely used in research (e.g., epidemiology) and business (e.g., recommender systems). However, sharing these graphs poses privacy risks because they contain sensitive information about individuals. Graph anonymization techniques aim to protect individual users in a graph, while graph de-anonymization aims to re-identify users. The effectiveness of anonymization and de-anonymization algorithms is usually evaluated with privacy metrics. However, it is unclear how strong existing privacy metrics are when they are used in graph privacy. In this paper, we study 26 privacy metrics for graph anonymization and de-anonymization and evaluate their strength in terms of three criteria: monotonicity indicates whether the metric indicates lower privacy for stronger adversaries; for within-scenario comparisons, evenness indicates whether metric values are spread evenly; and for between-scenario comparisons, shared value range indicates whether metrics use a consistent value range across scenarios. Our extensive experiments indicate that no single metric fulfills all three criteria perfectly. We therefore use methods from multi-criteria decision analysis to aggregate multiple metrics in a metrics suite, and we show that these metrics suites improve monotonicity compared to the best individual metric. This important result enables more monotonic, and thus more accurate, evaluations of new graph anonymization and de-anonymization algorithms.
A major impediment to research on improving peer review is the unavailability of peer-review data, since any release of such data must grapple with the sensitivity of the peer review data in terms of protecting identities of reviewers from authors. We posit the need to develop techniques to release peer-review data in a privacy-preserving manner. Identifying this problem, in this paper we propose a framework for privacy-preserving release of certain conference peer-review data -- distributions of ratings, miscalibration, and subjectivity -- with an emphasis on the accuracy (or utility) of the released data. The crux of the framework lies in recognizing that a part of the data pertaining to the reviews is already available in public, and we use this information to post-process the data released by any privacy mechanism in a manner that improves the accuracy (utility) of the data while retaining the privacy guarantees. Our framework works with any privacy-preserving mechanism that operates via releasing perturbed data. We present several positive and negative theoretical results, including a polynomial-time algorithm for improving on the privacy-utility tradeoff.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
