Related papers: Differential Aggregation against General Colluding…
Sensitive statistics are often collected across sets of users, with repeated collection of reports done over time. For example, trends in users' private preferences or software usage may be monitored via such reports. We study the…
Privacy-preserving data analysis has become a central challenge in modern statistics. At the same time, a long-standing goal in statistics is the development of adaptive procedures -- methods that achieve near-optimal performance across…
The development of Internet technology enables an analysis on the whole population rather than a certain number of samples, and leads to increasing requirement for privacy protection. Local differential privacy (LDP) is an effective…
Differential Privacy (DP) was originally developed to protect privacy. However, it has recently been utilized to secure machine learning (ML) models from poisoning attacks, with DP-SGD receiving substantial attention. Nevertheless, a…
Data poisoning attacks aim at manipulating model behaviors through distorting training data. Previously, an aggregation-based certified defense, Deep Partition Aggregation (DPA), was proposed to mitigate this threat. DPA predicts through an…
Location data is collected from users continuously to understand their mobility patterns. Releasing the user trajectories may compromise user privacy. Therefore, the general practice is to release aggregated location datasets. However,…
Secure aggregation (SecAgg) is a commonly-used privacy-enhancing mechanism in federated learning, affording the server access only to the aggregate of model updates while safeguarding the confidentiality of individual updates. Despite…
Local differential privacy (LDP) enables private data sharing and analytics without the need for a trusted data collector. Error-optimal primitives (for, e.g., estimating means and item frequencies) under LDP have been well studied. For…
The shuffle model of local differential privacy is an advanced method of privacy amplification designed to enhance privacy protection with high utility. It achieves this by randomly shuffling sensitive data, making linking individual data…
Public intelligent services enabled by machine learning algorithms are vulnerable to model extraction attacks that can steal confidential information of the learning models through public queries. Differential privacy (DP) has been…
Local differential privacy~(LDP) is an information-theoretic privacy definition suitable for statistical surveys that involve an untrusted data curator. An LDP version of quasi-maximum likelihood estimator~(QMLE) has been developed, but the…
Federated machine learning leverages edge computing to develop models from network user data, but privacy in federated learning remains a major challenge. Techniques using differential privacy have been proposed to address this, but bring…
Differential privacy protects an individual's privacy by perturbing data on an aggregated level (DP) or individual level (LDP). We report four online human-subject experiments investigating the effects of using different approaches to…
Conventional gradient-sharing approaches for federated learning (FL), such as FedAvg, rely on aggregation of local models and often face performance degradation under differential privacy (DP) mechanisms or data heterogeneity, which can be…
The objective of differential privacy (DP) is to protect privacy by producing an output distribution that is indistinguishable between any two neighboring databases. However, traditional differentially private mechanisms tend to produce…
As data-driven technologies advance swiftly, maintaining strong privacy measures becomes progressively difficult. Conventional $(\epsilon, \delta)$-differential privacy, while prevalent, exhibits limited adaptability for many applications.…
Differential Privacy (DP) provides tight upper bounds on the capabilities of optimal adversaries, but such adversaries are rarely encountered in practice. Under the hypothesis testing/membership inference interpretation of DP, we examine…
We present new auditors to assess Differential Privacy (DP) of an algorithm based on output samples. Such empirical auditors are common to check for algorithmic correctness and implementation bugs. Most existing auditors are batch-based or…
Collecting and analyzing evolving longitudinal data has become a common practice. One possible approach to protect the users' privacy in this context is to use local differential privacy (LDP) protocols, which ensure the privacy protection…
Differentially private (DP) mechanisms protect individual-level information by introducing randomness into the statistical analysis procedure. Despite the availability of numerous DP tools, there remains a lack of general techniques for…