Hamed Haddadi

A Tandem Framework Balancing Privacy and Security for Voice User Interfaces

2021 · arXiv (Cornell University)

Speech synthesis, voice cloning, and voice conversion techniques present severe privacy and security threats to users of voice user interfaces (VUIs). These techniques transform one or more elements of a speech signal, e.g., identity and …

Quantifying and Localizing Usable Information Leakage from Neural Network Gradients

2021 · arXiv (Cornell University)

In collaborative learning, clients keep their data private and communicate only the computed gradients of the deep neural network being trained on their local data. Several recent attacks show that one can still extract private …

Stronger Privacy for Federated Collaborative Filtering with Implicit\n Feedback

2021 · arXiv (Cornell University)

Recommender systems are commonly trained on centrally collected user\ninteraction data like views or clicks. This practice however raises serious\nprivacy concerns regarding the recommender's collection and handling of\npotentially sensitive data. Several privacy-aware recommender systems have been\nproposed …

Analysing Fairness of Privacy-Utility Mobility Models

2023 · arXiv (Cornell University)

Preserving the individuals' privacy in sharing spatial-temporal datasets is critical to prevent re-identification attacks based on unique trajectories. Existing privacy techniques tend to propose ideal privacy-utility tradeoffs, however, largely ignore the fairness implications of mobility …