Privacy
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Optimal conversion from R\'enyi Differential Privacy to $f$-Differential Privacy
arXiv:2602.04562v3 Announce Type: replace Abstract: We prove the conjecture stated in Appendix F.3 of \citet{zhu2022optimalaccountingdifferentialprivacy}: among all conversion rules that map a R\'enyi Differential Privacy (RDP) profile $\tau \mapsto \rho(\tau)$ to a valid hypothesis-testing trade-off $f$, the rule based on the intersection of single-order RDP privacy regions is optimal. This optimality holds simultaneously for all valid RDP profiles and for all Type I error levels $\alpha$....
Privacy-Aware Decoding: Mitigating Privacy Leakage of Large Language Models in Retrieval-Augmented Generation
arXiv:2508.03098v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) enhances the factual accuracy of large language models (LLMs) by conditioning outputs on external knowledge sources. However, when retrieval involves private or sensitive data, RAG systems are susceptible to extraction attacks that can leak confidential information through generated responses. We propose Privacy-Aware Decoding (PAD), a lightweight, inference-time defense that adaptively injects...
Optimal quantum locally differentially private mechanisms in the high-privacy regime
arXiv:2605.27278v2 Announce Type: replace-cross Abstract: We optimize the trade-off between privacy and utility in the high-privacy regime. We adopt local differential privacy (LDP) and its quantum extension, quantum local differential privacy (QLDP), for privacy protection, and investigate utility functions including the Holevo information (which reduces to the mutual information in the classical case) and the error exponents in symmetric and asymmetric hypothesis testing. These utility...
Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation
arXiv:2509.25906v2 Announce Type: replace Abstract: Federated Learning (FL) often adopts differential privacy (DP) to protect client data, but the added noise required for privacy guarantees can substantially degrade model accuracy. To resolve this challenge, we propose model-splitting privacy-amplified federated learning (MS-PAFL), a novel framework that combines structural model splitting with statistical privacy amplification. In this framework, each client's model is partitioned into a...
MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Models
arXiv:2511.16940v3 Announce Type: replace Abstract: Modern Vision-Language Models (VLMs) pose significant individual-level privacy risks by linking fragmented multimodal data to identifiable individuals through hierarchical chain-of-thought reasoning. However, existing privacy benchmarks remain structurally insufficient for this threat, as they primarily evaluate privacy perception while failing to address the more critical risk of privacy reasoning: a VLM's ability to infer and link...
Accuracy-First R\'enyi Differential Privacy and Post-Processing Immunity
arXiv:2509.22213v2 Announce Type: replace Abstract: The accuracy-first perspective of differential privacy addresses an important shortcoming by allowing a data analyst to adaptively adjust the quantitative privacy bound instead of sticking to a predetermined bound. Existing works on the accuracy-first perspective have neglected an important property of differential privacy known as post-processing immunity, which ensures that an adversary is not able to weaken the privacy guarantee by...
Persuasive Privacy
Announce Type: replace-cross Abstract: We propose a novel framework for measuring privacy from a Bayesian game-theoretic perspective. This framework enables the creation of new, purpose-driven privacy definitions that are rigorously justified, while also allowing for the assessment of existing privacy guarantees through game theory. We show that pure and probabilistic differential privacy are special cases of our framework, and provide new interpretations of the post-processing inequality in...
Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregation
arXiv:2604.07125v2 Announce Type: replace Abstract: This article presents DDP-SA, a scalable privacy-preserving federated learning framework that jointly leverages client-side local differential privacy (LDP) and full-threshold additive secret sharing (ASS) for secure aggregation. Unlike existing methods that rely solely on differential privacy or on secure multi-party computation (MPC), DDP-SA integrates both techniques to deliver stronger end-to-end privacy guarantees while remaining...
Composition for Pufferfish Privacy
arXiv:2602.02718v2 Announce Type: replace Abstract: When creating public data products out of confidential datasets, inferential/posterior-based privacy definitions, such as Pufferfish, provide compelling privacy semantics for data with correlations. However, such privacy definitions are rarely used in practice because they do not always compose. For example, it is possible to design algorithms for these privacy definitions that have no leakage when run once but reveal the entire dataset...
Musk’s Grok accused of violating Canadian privacy laws on deepfakes
Musk’s Grok accused of violating Canadian privacy laws on deepfakes Privacy watchdog finds xAI’s Grok lacks safeguards for sexualised deepfake image sharing, amid growing global scrutiny. xAI’s Grok has violated Canadian privacy laws because it launched an image generator that can create and share sexualised deepfake images without users’ consent, according to a report by the country’s privacy commissioner following a January probe. The official report, which was released on Thursday, comes...