AHEAD: Adaptive Hierarchical Decomposition for Range Query under Local Differential Privacy

Du, Linkang; Zhang, Zhikun; Bai, Shaojie; Liu, Changchang; Ji, Shouling; Cheng, Peiyao; Chen, Jiming

doi:10.1145/3460120.3485668

Cited by 18 publications

(5 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the algorithm in [8] only applies to learning algorithms that can be transformed into summation form, limiting itself not for neural networks. Recently, Ginart et al [19] have proposed the notion of (𝜖, 𝛿)approximate unlearning in a way reminiscent of DP [15,16,54,65,66]. It guarantees that the output distribution of the unlearned model is close to the model trained without the revoked samples.…”

Section: Related Workmentioning

confidence: 99%

Graph Unlearning

Chen

Zhang

Wang

et al. 2022

Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security

Self Cite

View full text Add to dashboard Cite

Machine unlearning is a process of removing the impact of some training data from the machine learning (ML) models upon receiving removal requests. While straightforward and legitimate, retraining the ML model from scratch incurs a high computational overhead. To address this issue, a number of approximate algorithms have been proposed in the domain of image and text data, among which SISA is the state-of-the-art solution. It randomly partitions the training set into multiple shards and trains a constituent model for each shard. However, directly applying SISA to the graph data can severely damage the graph structural information, and thereby the resulting ML model utility. In this paper, we propose GraphEraser, a novel machine unlearning framework tailored to graph data. Its contributions include two novel graph partition algorithms and a learning-based aggregation method. We conduct extensive experiments on five real-world graph datasets to illustrate the unlearning efficiency and model utility of GraphEraser. It achieves 2.06× (small dataset) to 35.94× (large dataset) unlearning time improvement. On the other hand, GraphEraser achieves up to 62.5% higher F1 score and our proposed learning-based aggregation method achieves up to 112% higher F1 score. 1 CCS CONCEPTS• Security and privacy; • Computing methodologies → Machine learning;

show abstract

Section: Related Workmentioning

confidence: 99%

Graph Unlearning

Chen

Zhang

Wang

et al. 2022

Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security

Self Cite

View full text Add to dashboard Cite

show abstract

“…Ono et al [44] integrated differential privacy [71], [68], [62] into the distributed RL algorithm to defend the extraction. The local models report noisy gradients designed to satisfy local differential privacy [13], [14], [64], [70], i.e., keeping the local information from being exploited by adversarial reverse engineering. Chen et al [8] proposed a novel testing framework for deep learning copyright protection, which can be adjusted to detect the knowledge extraction against DRL.…”

Section: Related Workmentioning

confidence: 99%

ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement Learning

Du,

Chen,

Sun

et al. 2024

Proceedings 2024 Network and Distributed System Security Symposium

View full text Add to dashboard Cite

Data is a critical asset in AI, as high-quality datasets can significantly improve the performance of machine learning models. In safety-critical domains such as autonomous vehicles, offline deep reinforcement learning (offline DRL) is frequently used to train models on pre-collected datasets, as opposed to training these models by interacting with the real-world environment as the online DRL. To support the development of these models, many institutions make datasets publicly available with opensource licenses, but these datasets are at risk of potential misuse or infringement. Injecting watermarks to the dataset may protect the intellectual property of the data, but it cannot handle datasets that have already been published and is infeasible to be altered afterward. Other existing solutions, such as dataset inference and membership inference, do not work well in the offline DRL scenario due to the diverse model behavior characteristics and offline setting constraints.In this paper, we advocate a new paradigm by leveraging the fact that cumulative rewards can act as a unique identifier that distinguishes DRL models trained on a specific dataset. To this end, we propose ORL-AUDITOR, which is the first trajectorylevel dataset auditing mechanism for offline RL scenarios. Our experiments on multiple offline DRL models and tasks reveal the efficacy of ORL-AUDITOR, with auditing accuracy over 95% and false positive rates less than 2.88%. We also provide valuable insights into the practical implementation of ORL-AUDITOR by studying various parameter settings. Furthermore, we demonstrate the auditing capability of ORL-AUDITOR on open-source datasets from Google and DeepMind, highlighting its effectiveness in auditing published datasets. ORL-AUDITOR is open-sourced at https://github.com/link-zju/ORL-Auditor. I. INTRODUCTIONDeep reinforcement learning (DRL) has been successfully applied to many complex decision-making tasks, such as autopilot [16], robot control [3], [50], power systems [69], intrusions detection [41], [66].

show abstract

“…Differential privacy [35] is a promising approach to enforcing privacy regulations [26], providing strong statistical privacy guarantees. However, being statistical, these guarantees may be practically insufficient or of limited usability depending on the data type, the size of datasets, and the queries considered [33,34,76].…”

Section: Related Workmentioning

confidence: 99%

User-Controlled Privacy: Taint, Track, and Control

Hublet,

Basin,

Krstić

2024

PoPETs

View full text Add to dashboard Cite

We develop the first language-based, Privacy by Design approach that provides support for a rich class of privacy policies. The policies are user-defined, rather than programmer-defined, and support fine-grained information flow restrictions (considering individual application inputs and outputs) with temporal constraints. Our approach, called Taint, Track, and Control (TTC), combines dynamic information-flow control and runtime verification to enforce these policies in the presence of malicious users and developers. We provide TTC's semantics and proofs of its correct enforcement, formalized in the Isabelle/HOL proof assistant. We also implement our approach in a web development framework and port three baseline applications from previous work into this framework for evaluation. Overall, our approach enforces expressive user-defined privacy policies with practical runtime performance.

show abstract

AHEAD: Adaptive Hierarchical Decomposition for Range Query under Local Differential Privacy

Cited by 18 publications

References 64 publications

Graph Unlearning

Graph Unlearning

ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement Learning

User-Controlled Privacy: Taint, Track, and Control

Contact Info

Product

Resources

About