The field of privacy protection and secure aggregation is rapidly evolving, with a focus on developing innovative methods to protect sensitive information and prevent adversarial attacks. Recent research has explored the use of pointwise maximal leakage privacy, differential privacy, and mutual-information privacy to protect the privacy of discrete-time linear time-invariant systems and federated learning models.

Noteworthy papers in this area include the proposal of a new systematic approach to protect the privacy of discrete-time linear time-invariant systems against adversaries knowledgeable of the system's prior information, and the development of Armadillo, a secure aggregation system that provides disruptive resistance against adversarial clients.

Other significant contributions include the introduction of HetDAPAC, a framework that leverages attribute heterogeneity in distributed attribute-based private access control, and the development of ModularSubsetSelection, a new algorithm for locally differentially private frequency estimation.

The Capacity of Collusion-Resilient Decentralized Secure Aggregation with Groupwise Keys and Mutual Information Bounds in the Shuffle Model are also significant contributions to the field, providing insights into the fundamental limits of decentralized secure aggregation and the information-theoretic bounds of the shuffle model.