James Joshi

Liou Tang, James Joshi, Ashish Kundu

The removal of learned data from Machine Learning models through Machine Unlearning (MU) has been widely studied; however, there has yet to be an agreed-upon scheme for auditing MU. Existing work has shown that a dishonest model owner can falsify evidence to avoid executing MU, while curious auditors (and adversaries) can infer the privacy-sensitive properties of the model and its training data even with limited access. Yet auditing of MU under mutual distrust between the model owner and the auditor remains unexplored. We provide an information-theoretic proof for this scenario: for convex ML models, a generic audit scheme that relies solely on querying the model for \textit{behavioral} signals cannot identify insufficiently unlearned models without revealing membership information of the retained set. Therefore, auditing MU under the assumption of a dishonest model owner and an honest-but-curious auditor faces an inherent privacy-audit tradeoff. Our empirical results on convex models strongly supports this result, while further experiments demonstrate that this privacy-audit tension persists in non-convex models. Our results call for a more careful consideration of the privacy-audit tension under a realistic auditor threat model, and serve as a foundation for more scrutiny of designs of privacy-preserving audit schemes for the MU pipeline. We also release our code implementation at https://github.com/LiouTang/Behavioral-Unlearn-Audit.

Runhua Xu, Shiqi Gao, Chao Li et al.

Federated learning (FL) is inherently susceptible to privacy breaches and poisoning attacks. To tackle these challenges, researchers have separately devised secure aggregation mechanisms to protect data privacy and robust aggregation methods that withstand poisoning attacks. However, simultaneously addressing both concerns is challenging; secure aggregation facilitates poisoning attacks as most anomaly detection techniques require access to unencrypted local model updates, which are obscured by secure aggregation. Few recent efforts to simultaneously tackle both challenges offen depend on impractical assumption of non-colluding two-server setups that disrupt FL's topology, or three-party computation which introduces scalability issues, complicating deployment and application. To overcome this dilemma, this paper introduce a Dual Defense Federated learning (DDFed) framework. DDFed simultaneously boosts privacy protection and mitigates poisoning attacks, without introducing new participant roles or disrupting the existing FL topology. DDFed initially leverages cutting-edge fully homomorphic encryption (FHE) to securely aggregate model updates, without the impractical requirement for non-colluding two-server setups and ensures strong privacy protection. Additionally, we proposes a unique two-phase anomaly detection mechanism for encrypted model updates, featuring secure similarity computation and feedback-driven collaborative selection, with additional measures to prevent potential privacy breaches from Byzantine clients incorporated into the detection process. We conducted extensive experiments on various model poisoning attacks and FL scenarios, including both cross-device and cross-silo FL. Experiments on publicly available datasets demonstrate that DDFed successfully protects model privacy and effectively defends against model poisoning threats.

Runhua Xu, Chao Li, James Joshi

Increasingly, information systems rely on computational, storage, and network resources deployed in third-party facilities such as cloud centers and edge nodes. Such an approach further exacerbates cybersecurity concerns constantly raised by numerous incidents of security and privacy attacks resulting in data leakage and identity theft, among others. These have, in turn, forced the creation of stricter security and privacy-related regulations and have eroded the trust in cyberspace. In particular, security-related services and infrastructures, such as Certificate Authorities (CAs) that provide digital certificate services and Third-Party Authorities (TPAs) that provide cryptographic key services, are critical components for establishing trust in crypto-based privacy-preserving applications and services. To address such trust issues, various transparency frameworks and approaches have been recently proposed in the literature. This paper proposes TAB framework that provides transparency and trustworthiness of third-party authority and third-party facilities using blockchain techniques for emerging crypto-based privacy-preserving applications. TAB employs the Ethereum blockchain as the underlying public ledger and also includes a novel smart contract to automate accountability with an incentive mechanism that motivates users to participate in auditing, and punishes unintentional or malicious behaviors. We implement TAB and show through experimental evaluation in the Ethereum official test network, Rinkeby, that the framework is efficient. We also formally show the security guarantee provided by TAB, and analyze the privacy guarantee and trustworthiness it provides.