R Impagliazzo, R Lei, T Pitassi, J Sorrell - Proceedings of the 54th annual …, 2022 - dl.acm.org
We introduce the notion of a reproducible algorithm in the context of learning. A reproducible learning algorithm is resilient to variations in its samples—with high probability, it returns the …
We present DP-Sniper, a practical black-box method that automatically finds violations of differential privacy. DP-Sniper is based on two key ideas:(i) training a classifier to predict if …
J Lokna, A Paradis, DI Dimitrov, M Vechev - Proceedings of the 2023 …, 2023 - dl.acm.org
(ε, δ) differential privacy has seen increased adoption recently, especially in private machine learning applications. While this privacy definition allows provably limiting the amount of …
Corporations, organizations, and governments have collected, digitized, and stored information in digital forms since the invention of computers, and the speed of such data …
Over the last decade, differential privacy has achieved widespread adoption within the privacy community. Moreover, it has attracted significant attention from the verification …
This paper presents Orchard, a system that can answer queries about sensitive data that is held by millions of user devices, with strong differential privacy guarantees. Orchard …
D Zhang, D Kifer - Proceedings of the 44th ACM SIGPLAN Symposium …, 2017 - dl.acm.org
The growing popularity and adoption of differential privacy in academic and industrial settings has resulted in the development of increasingly sophisticated algorithms for …
Establishing quantitative bounds on the execution cost of programs is essential in many areas of computer science such as complexity analysis, compiler optimizations, security and …
D Hardy, T Piquet, I Puaut - 2009 30th IEEE Real-Time Systems …, 2009 - ieeexplore.ieee.org
Multi-core chips have been increasingly adopted by the microprocessor industry. For real- time systems to exploit multi-core architectures, it is required to obtain both tight and safe …