MohammadMahdi Jahanara

Vahid R. Asadi, Marco L. Carmosino, Mohammadmahdi Jahanara et al.

Protecting the privacy of people whose data is used by machine learning algorithms is important. Differential Privacy is the appropriate mathematical framework for formal guarantees of privacy, and boosted decision trees are a popular machine learning technique. So we propose and test a practical algorithm for boosting decision trees that guarantees differential privacy. Privacy is enforced because our booster never puts too much weight on any one example; this ensures that each individual's data never influences a single tree "too much." Experiments show that this boosting algorithm can produce better model sparsity and accuracy than other differentially private ensemble classifiers.

MohammadJavad Hajialikhani, MohammadMahdi Jahanara

Bitcoin and Ethereum are novel mechanisms for decentralizing the concept of money and computation. Extending decentralization to the human identity concept, we can think of using blockchain for creating a list of verified human identities with a one-person-one-ID property. UniqueID is a Decentralized Autonomous Organization(DAO) for maintaining human identities such that every physical human entity can have no more that one account. One part of this identity is simply the user's claim on one of his unique, permanent, and measurable characteristics -biometrics. Blockchain has proved its integrity as a platform for storing and performing computations on such claims. The biggest challenge here is to ensure that the user has submitted his own valid biometric data. Human verifiers can check if there is any inconsistency in other users' data, by peer-to-peer checks. For preventing bad behavior and centralization in the verification process, UniqueID benefits from novel governance mechanisms to choose verifiers and punish unjust ones. Also, there are incentives for honest verifiers and users by newly generated tokens. We show how the users' privacy can be preserved by using state-of-the-art cryptographic techniques, and so they can use their identity without any concerns for votings, financial and banking purposes, social media accounts, reputation systems etc.