Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy
Differentially private (DP) mechanisms are difficult to interpret and calibrate because existing methods for mapping standard privacy parameters to concrete privacy risks -- re-identification, attribute inference, and data reconstruction -- are both overly pessimistic and inconsistent. In this work, we use the hypothesis-testing interpretation of DP ($f$-DP), and determine that bounds on attack success can take the same unified form across re-identification, attribute inference, and data reconstruction risks. Our unified bounds are (1) consistent across a multitude of attack settings, and (2) tunable, enabling practitioners to evaluate risk with respect to arbitrary, including worst-case, levels of baseline risk. Empirically, our results are tighter than prior methods using $\varepsilon$-DP, Rényi DP, and concentrated DP. As a result, calibrating noise using our bounds can reduce the required noise by 20% at the same risk level, which yields, e.g., an accuracy increase from 52% to 70% in a text classification task. Overall, this unifying perspective provides a principled framework for interpreting and calibrating the degree of protection in DP against specific levels of re-identification, attribute inference, or data reconstruction risk.
Code (0)
등록된 구현이 없습니다.
Tasks
Text ClassificationSimilar Papers 제목 키워드 기반
Matrix-Driven Identification and Reconstruction of LLM Weight Homology
We propose Matrix-Driven Identification and Reconstruction (MDIR), a SOTA large language model homology method that accurately detects weight correspondences between models and provides rigorous $p$-value estimation of t…
SoK: Reconstruction Attacks on Synthetic Tabular Data (Insights from Winning the NIST CRC)
Synthetic data is increasingly promoted as a privacy-preserving substitute for releasing sensitive tabular records, yet its central adversarial threat ("reconstruction", the recovery of an individual's hidden attribute v…
Synthetic Data GenerationLocal Model Reconstruction Attacks in Federated Learning and their Uses
In this paper, we initiate the study of local model reconstruction attacks for federated learning, where a honest-but-curious adversary eavesdrops the messages exchanged between a targeted client and the server, and then…
AttributeEarnings ClassificationFederated LearningInference Attack+2Identity-Aware Attribute Recognition via Real-Time Distributed Inference in Mobile Edge Clouds
With the development of deep learning technologies, attribute recognition and person re-identification (re-ID) have attracted extensive attention and achieved continuous improvement via executing computing-intensive deep…
AttributePedestrian Attribute RecognitionPerson IdentificationPerson Re-IdentificationG$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning
Vision-Language Models (VLMs) still lack robustness in spatial intelligence, demonstrating poor performance on spatial understanding and reasoning tasks. We attribute this gap to the absence of a visual geometry learning…
Spatial Reasoning3D Reconstruction3D scene Editing