Differential Privacy under Incalculable Sensitivity

Artificial Intelligence (AI) has attracted a large amount of attention in recent years. However, several new problems, such as privacy violations, security issues, or effectiveness, have been emerging. Differential privacy has several attractive properties that make it quite valuable for AI, such as privacy preservation, security, randomization, composition, and stability. Therefore, this paper presents differential privacy mechanisms for multi-agent systems, reinforcement learning, and knowledge transfer based on those properties, which proves that current AI can benefit from differential privacy mechanisms. In addition, the previous usage of differential privacy mechanisms in private machine learning, distributed machine learning, and fairness in models is discussed, bringing several possible avenues to use differential privacy mechanisms in AI. The purpose of this paper is to deliver the initial idea of how to integrate AI with differential privacy mechanisms and to explore more possibilities to improve AIs performance.

Differential privacy is often used in location privacy protection because of its strict reasoning and proof privacy guarantee. When users make continuous location query, it will cause noise superposition, which leads to the decline of query accuracy. At present, although differential privacy based on rule tree structure can reduce the query error, it will generate a lot of invalid zero nodes. The data structure is too large, and more improvement in the query accuracy can be further investigated. In this paper, we proposed a differential privacy location privacy protection method based on generative adversary network. Firstly, the definition of location data privacy protection under differential privacy mechanism is given, and then resume density aware network under differential privacy mechanism. Based on density aware network, the privacy protection problem of location data can be transformed into the distribution of fitting trajectory length. Finally, we use Markov chain to generate a new trajectory, and introduce the generative adversarial network to construct a set differential privacy protection method. Compared with other methods to improve the accuracy of differential privacy query, this method can effectively reduce the problem of query accuracy decline caused by noise superposition in continuous query, and can adapt to lbs location query service in different density environments.KeywordsGenerative adversarial networkLocation differencePrivacy protectionMarkov chainDensity aware network

New generation head-mounted displays, such as VR and AR glasses, are coming into the market with already integrated eye tracking and are expected to enable novel ways of human-computer interaction in numerous applications. However, since eye movement properties contain biometric information, privacy concerns have to be handled properly. Privacy-preservation techniques such as differential privacy mechanisms have recently been applied to eye movement data obtained from such displays. Standard differential privacy mechanisms; however, are vulnerable due to temporal correlations between the eye movement observations. In this work, we propose a novel transform-coding based differential privacy mechanism to further adapt it to the statistics of eye movement feature data and compare various low-complexity methods. We extend the Fourier perturbation algorithm, which is a differential privacy mechanism, and correct a scaling mistake in its proof. Furthermore, we illustrate significant reductions in sample correlations in addition to query sensitivities, which provide the best utility-privacy trade-off in the eye tracking literature. Our results provide significantly high privacy without any essential loss in classification accuracies while hiding personal identifiers.

OPTDP: Towards optimal personalized trajectory differential privacy for trajectory data publishing

This paper considers the problem of secure data aggregation (mainly summation) in a distributed setting, while ensuring differential privacy of the result. We study secure multiparty addition protocols using well known security schemes: Shamir's secret sharing, perturbation-based, and various encryptions. We supplement our study with our new enhanced encryption scheme EFT, which is efficient and fault tolerant. Differential privacy of the final result is achieved by either distributed Laplace or Geometric mechanism (respectively DLPA or DGPA), while approximated differential privacy is achieved by diluted mechanisms. Distributed random noise is generated collectively by all participants, which draw random variables from one of several distributions: Gamma, Gauss, Geometric, or their diluted versions. We introduce a new distributed privacy mechanism with noise drawn from the Laplace distribution, which achieves smaller redundant noise with efficiency. We compare complexity and security characteristics of the protocols with different differential privacy mechanisms and security schemes. More importantly, we implemented all protocols and present an experimental comparison on their performance and scalability in a real distributed environment. Based on the evaluations, we identify our security scheme and Laplace DLPA as the most efficient for secure distributed data aggregation with privacy.

The increasing complexity and dynamic nature of cyber threats in zero-trust architectures necessitates a more adaptive approach to differential privacy mechanisms. Current static privacy solutions fail to adequately address evolving threat landscapes, leading to potential vulnerabilities and reduced system efficiency. This research presents a novel adaptive differential privacy framework that dynamically adjusts privacy parameters based on real-time threat assessment within zero-trust environments. Our solution introduces an intelligent privacy budget optimization algorithm that continuously evaluates threat levels and automatically recalibrates privacy mechanisms to maintain optimal protection while minimizing performance overhead. Through extensive experimental evaluation using real-world datasets and simulated attack scenarios, we demonstrate that our adaptive approach achieves a 47% improvement in privacy preservation compared to static mechanisms, while maintaining system performance within acceptable thresholds. The framework successfully detects and responds to 94% of emerging threats within milliseconds, dynamically adjusting privacy parameters to counter identified risks. Our results show that the proposed solution effectively balances privacy protection, system performance, and threat responsiveness in zero-trust architectures. Additionally, we provide comprehensive implementation guidelines and identified key challenges for deploying adaptive differential privacy mechanisms in production environments. This research contributes to the advancement of privacy-preserving systems by introducing a practical, scalable solution for managing differential privacy in dynamic threat landscapes.

As machine learning systems become increasingly prevalent in privacy-sensitive domains, the need for training high-performance models while preserving individual privacy has become paramount. This paper presents a comprehensive analysis of federated learning combined with differential privacy mechanisms, addressing the fundamental tension between model utility and privacy protection. We propose an adaptive noise calibration framework that dynamically adjusts privacy parameters based on model convergence patterns and client heterogeneity. Through extensive experiments on benchmark datasets, we demonstrate that our approach achieves superior privacy-utility trade-offs compared to existing methods, maintaining competitive model accuracy while providing strong theoretical privacy guarantees. Our results show that careful calibration of differential privacy parameters can reduce the performance degradation typically associated with privacy-preserving federated learning from 15-20% to 5-8% across various machine learning tasks.

Sentence embeddings represent the meaning of a given sentence using a fixed dimensional vector. Different approaches have been proposed in the Natural Language Processing (NLP) community for learning encoders that can produce accurate sentence embeddings that perform well for diverse downstream tasks requiring sentence representations. Despite prior work focusing mainly on creating accurate sentence embeddings, how to keep private the sensitive information contained in the sentences remains an unexplored research problem. In this article, we propose Covering Metric Analytic Gaussian (CMAG), a covering metric Differential Privacy (DP) mechanism for sentence embeddings such that minimal random noise is added to a set of sentence embeddings produced by an encoder to protect the private information expressed in those sentences. Given a sentence embedding s , CMAG considers the Mahalanobis distance between s and the other sentence embeddings s ’ in the local neighbourhood of s to determine the minimal amount of random noise that must be added to s to obtain provable metric DP guarantees. Experimental results show that the proposed DP mechanism protects private information better than previously proposed DP mechanisms while reporting good performance in a broad range of downstream NLP tasks.

Differential privacy is a precise mathematical constraint meant to ensure privacy of individual pieces of information in a database even while queries are being answered about the aggregate. Intuitively, one must come to terms with what differential privacy does and does not guarantee. For example, the definition prevents a strong adversary who knows all but one entry in the database from further inferring about the last one. This strong adversary assumption can be overlooked, resulting in misinterpretation of the privacy guarantee of differential privacy. Herein we give an equivalent definition of privacy using mutual information that makes plain some of the subtleties of differential privacy. The mutual-information differential privacy is in fact sandwiched between $\epsilon$-differential privacy and $(\epsilon,\delta)$-differential privacy in terms of its strength. In contrast to previous works using unconditional mutual information, differential privacy is fundamentally related to conditional mutual information, accompanied by a maximization over the database distribution. The conceptual advantage of using mutual information, aside from yielding a simpler and more intuitive definition of differential privacy, is that its properties are well understood. Several properties of differential privacy are easily verified for the mutual information alternative, such as composition theorems.

The primary motivation is to address difficulties in data interpretation or a reduction in model accuracy. Although differential privacy can provide data privacy guarantees, it also creates problems. Thus, we need to consider the noise setting for differential privacy is currently inconclusive. This paper’s main contribution is finding a balance between privacy and accuracy. The training data of deep learning models may contain private or sensitive corporate information. These may be dangerous to attacks, leading to privacy data leakage for data sharing. Many strategies are for privacy protection, and differential privacy is the most widely applied one. Google proposed a federated learning technology to solve the problem of data silos in 2016. The technology can share information without exchanging original data and has made significant progress in the medical field. However, there is still the risk of data leakage in federated learning; thus, many models are now used with differential privacy mechanisms to minimize the risk. The data in the financial field are similar to medical data, which contains a substantial amount of personal data. The leakage may cause uncontrollable consequences, making data exchange and sharing difficult. Let us suppose that differential privacy applies to the financial field. Financial institutions can provide customers with higher value and personalized services and automate credit scoring and risk management. Unfortunately, the economic area rarely applies differential privacy and attains no consensus on parameter settings. This study compares data security with non-private and differential privacy financial visual models. The paper finds a balance between privacy protection with model accuracy. The results show that when the privacy loss parameter ϵ is between 12.62 and 5.41, the privacy models can protect training data, and the accuracy does not decrease too much.

The logistic model is a very elementary and important model in the field of machine learning. In this article, an efficient differential privacy logistic classification mechanism is proposed. The proposed mechanism is better than object function perturbation mechanism in terms of running time and accuracy. Regarding accuracy, the proposed mechanism's accuracy is almost the same as the no differential privacy (non-dp) mechanism, and the proposed mechanism is better than that of the object function perturbation mechanism in both the test accuracy and the train accuracy. As for the running time of the training model, the proposed mechanism is better than the object function mechanism and is the same as the non-dp mechanism.

A verifiable scheme for differential privacy based on zero-knowledge proofs

Differential privacy is a statistical definition of privacy that has attracted the interest of both academia and industry. Its formulations are easy to understand, but the differential privacy of databases is complicated to determine. One of the reasons for this is that small changes in database programs can break their differential privacy. Therefore, formal verification of differential privacy has been studied for over a decade. In this paper, we propose an Isabelle/HOL library for formalizing differential privacy in a general setting. To our knowledge, it is the first formalization of differential privacy that supports continuous probability distributions. First, we formalize the standard definition of differential privacy and its basic properties. Second, we formalize the Laplace mechanism and its differential privacy. Finally, we formalize the differential privacy of the report noisy max mechanism.

Motivated by traffic analysis attacks based on the packet sizes and timing information in the Internet of Things (IoT) networks, we establish a rigorous event-level differential privacy (DP) model on infinite packet streams. We propose a traffic shaper satisfying a first-come-first-served queuing discipline that outputs traffic dependent on the input using a DP mechanism. We show that in special cases the proposed mechanism recovers existing shapers which standardize the output independently from the input. To find the optimal shapers for given levels of privacy and transmission efficiency, we formulate the constrained problem of minimizing the expected delay per packet and propose using the expected queue size across time as a proxy. We further show that the constrained minimization is a convex program. We demonstrate the effect of shapers on both synthetic data and packet traces from actual IoT devices. The experimental results reveal inherent privacy-overhead tradeoffs: more shaping overhead provides better privacy protection. Under the same privacy level, there is a tradeoff between dummy traffic and delay. When shaping heavier or less bursty traffic, all shapers become more overhead-efficient. We also show that increased traffic from more IoT devices makes guaranteeing event-level privacy easier. The DP shaper offers tunable privacy that is invariant with the change in the input traffic distribution and has an advantage in handling burstiness over traffic-independent shapers. This approach accommodates heterogeneous network conditions and user demands in privacy and overhead.

Using the machine learning technology to explore the potential value of Big Data brings us into a smarter world, and the way data is mined through data sharing patterns also threatens the privacy of personal data. Differential privacy is a prevalent mechanism to effectively protect the personal data privacy due to the strict and the provable privacy definition, although there are several achievements have reached by combining the differential privacy and traditional machine learning algorithms in a stand-alone mode, little to talk about the distributed environment. To fill this gap, this paper proposes a method to embed the differential privacy mechanism into distributed platform, respectively implements the DPLloyd, GUPT k-means and GUPT logistic regression on the platform of Spark. The evaluation demonstrates that the approach barely interferes the effect of distributed machine learning algorithms and thus achieves the goal of differential privacy.