Protects user privacy in models using optional personal data.
problem Ensuring fairness for users who opt-out of data sharing.
method Formalizes protection requirements, introduces Protected User Consent (PUC), devises data augmentation strategy.
result PUC-compliant models can improve performance without disadvantaging opt-out users.
Protects proprietary policies from imitation learning by training adversarial policy ensembles.
problem Protecting policies from external observers cloning them.
method Introduces a reinforcement learning framework that trains an ensemble of near-optimal policies, making demonstrations useless for external observers.
result Demonstrates the existence of 'non-clonable' ensembles and provides a solution to the optimization problem.
Decor protects decentralized learning models from curious users.
problem Privacy violation in decentralized learning.
method Decor uses correlated Gaussian noises to protect local models in decentralized SGD with differential privacy guarantees.
result Decor matches central DP optimal privacy-utility trade-off for arbitrary connected graphs.
New algorithms protect user-level privacy in learning tasks.
problem Protecting user-level privacy in learning tasks with stringent constraints.
method Proposes algorithms for learning tasks under user-level differential privacy constraints.
result Privacy cost decreases as users provide more samples or as the number of users increases.
Machine Learning based Quality of Experience (QoE) models potentially suffer from over-fitting due to limitations including low data volume, and limited participant profiles. This prevents models from becoming generic. Consequently, these trained models may under-perform when tested outside the experimented population.…
Fawkes protects images from unauthorized facial recognition models.
problem Unauthorized training of facial recognition models poses privacy risks.
method Fawkes adds imperceptible pixel-level changes (cloaks) to images before release.
result Fawkes can protect images from misidentification by 95% and 80% even when clean images are leaked.
De-identification of electronic health records (EHR) is a vital step towards advancing health informatics research and maximising the use of available data. It is a two-step process where step one is the identification of protected health information (PHI), and step two is replacing such PHI with surrogates. Despite th…
Proposes element-level differential privacy for better privacy and utility in statistical learning.
problem Challenges of strong differential privacy in statistical learning applications.
method Introduces element-level differential privacy, extending classical DP to protect specific user elements.
result Provides better utility and more robust results compared to classical DP by allowing finer privacy protections.
This paper presents a method to generate synthetic data with differential privacy to protect user privacy while maintaining data trends.
problem Protecting user privacy while using real data for AI applications.
method Develops a practical guide to generating synthetic data using differential privacy.
result Synthetic data can be generated to preserve trends of real data while ensuring strong privacy protections.
PriRec preserves privacy in POI recommendation by keeping data and models on users' devices.
problem Privacy concerns in centralized POI recommendation models.
method Local differential privacy for sensitive data, secure decentralized gradient descent for linear models, secure aggregation for feature interactions.
result PriRec achieves comparable or better recommendation accuracy than FM while protecting user privacy.
Many mobile applications and virtual conversational agents now aim to recognize and adapt to emotions. To enable this, data are transmitted from users' devices and stored on central servers. Yet, these data contain sensitive information that could be used by mobile applications without user's consent or, maliciously, b…
A new framework reduces data upload for image classification while protecting user privacy.
problem Data upload limitations and privacy concerns in cloud-based image classification.
method Unsupervised autoencoder training at edge devices, followed by latent vector transmission to server for classifier training.
result The framework reduces communications overhead and protects user data privacy.
Develops privacy-preserving methods for longitudinal linear regression.
problem Protecting individual information in longitudinal data with privacy-preserving statistics.
method Proposes a user-level private regression estimator and a privatized covariance estimator for longitudinal linear regression under user-level differential privacy.
result Establishes theoretical guarantees for practical user-level differential privacy estimation and inference in longitudinal linear regression.
NTL protects AI models by restricting their generalization ability to specific domains.
problem Protecting AI models as intellectual property in a secure and robust manner.
method Non-Transferable Learning (NTL) captures exclusive data representation and restricts model generalization ability.
result NTL provides robust resistance to watermark removal and data-centric protection for usage authorization.
Secure federated learning framework resists adversarial users.
problem Resilience against adversarial (Byzantine) users in federated learning.
method Integrated stochastic quantization, verifiable outlier detection, and secure model aggregation.
result First single-server Byzantine-resilient secure aggregation framework (BREA) for secure federated learning.
This paper protects rankings from differential privacy breaches.
problem Leakage of personal information in rankings.
method Develops ε-ranking differential privacy and a multistage ranking algorithm.
result Establishes the connection between Mallows model and ε-ranking differential privacy.
This article examines methods to interpret complex models in insurance.
problem Ensuring transparency and understanding of data-driven decisions in insurance.
method Inventory of methods to interpret models, focusing on insurance applications.
result Increased interest in model transparency due to complex algorithms and GDPR requirements.
The paper proposes methods to infer from privacy-protected data using simulation-based techniques.
problem Valid statistical inference from privacy-protected data is computationally challenging.
method Simulation-based inference methods, including sequential Monte Carlo and neural conditional density estimators.
result Valid statistical inferences can be made from privacy-protected data.
Federated learning uses worst-case optimization to handle uncertain local data impacts.
problem Handling uncertainty in local data sets in federated learning.
method Reformulate FL problem using worst-case optimization theory, considering local data as uncertain functions bounded in a closed region.
result Comparison of FL performance with centralized learning and application of regularization factors.
The amount of personal data collected in our everyday interactions with connected devices offers great opportunities for innovative services fueled by machine learning, as well as raises serious concerns for the privacy of individuals. In this paper, we propose a massively distributed protocol for a large set of users …
FedConPE improves conversational recommender systems efficiency and privacy.
problem Efficiently eliciting user preferences in interactive systems with heterogeneous clients.
method Phase elimination-based federated conversational bandit algorithm with adaptive key term construction.
result Minimizes uncertainty across all dimensions in feature space and offers improved efficiency and privacy.
APGE protects graph node representations from inference attacks.
problem Privacy leakage in graph embedding methods.
method Adversarial training framework with disentangling and purging mechanisms.
result APGE preserves structural and utility attributes while concealing private information.
Secure Aggregation protocols allow a collection of mutually distrust parties, each holding a private value, to collaboratively compute the sum of those values without revealing the values themselves. We consider training a deep neural network in the Federated Learning model, using distributed stochastic gradient descen…
PASS protects private attributes by stochastically substituting data.
problem Protecting private attributes in ML services while maintaining data utility.
method PASS uses stochastic data substitution with a novel loss function derived from information theory.
result PASS effectively protects private attributes across various datasets.
Fair machine learning has become a significant research topic with broad societal impact. However, most fair learning methods require direct access to personal demographic data, which is increasingly restricted to use for protecting user privacy (e.g. by the EU General Data Protection Regulation). In this paper, we pro…
BCDP enhances privacy by protecting sensitive features more precisely.
problem Uniform privacy protection in LDP degrades performance for sensitive features.
method Bayesian Coordinate Differential Privacy (BCDP) adjusts privacy protection per feature sensitivity.
result BCDP improves accuracy in downstream tasks without sacrificing privacy.
LightSecAgg reduces secure aggregation complexity in FL.
problem Complexity in secure aggregation protocols for FL systems.
method One-shot aggregate-mask reconstruction via mask encoding/decoding.
result Significantly reduces overhead for resiliency against dropped users.
Federated approach protects privacy while learning user patterns.
problem Protecting sensitive data in recommendation systems.
method Differentially private prototypes for global and local models.
result Local adaptation improves recommendation accuracy and relevance.
Users in various web and mobile applications are vulnerable to attribute inference attacks, in which an attacker leverages a machine learning classifier to infer a target user's private attributes (e.g., location, sexual orientation, political view) from its public data (e.g., rating scores, page likes). Existing defen…
New algorithms protect user data while optimizing personalized decisions.
problem Personalized decision-making with private user data.
method Developed LDP algorithms for stochastic generalized linear bandits using SGD and OLS.
result Achieved the same regret bound as non-privacy settings with LDP.
With the widespread use of machine learning (ML) techniques, ML as a service has become increasingly popular. In this setting, an ML model resides on a server and users can query it with their data via an API. However, if the user's input is sensitive, sending it to the server is undesirable and sometimes even legally …
ML system reduces overdraft fees for Mint users.
problem Overdraft fees burden Americans, leading to financial hardship.
method ML-driven overdraft early warning system (ODEWS).
result Saved $3 million in overdraft fees for Mint customers.
Privacy attacks reveal hidden information in network embeddings after node removal.
problem Privacy concerns in network embeddings after node deletion.
method Analyzed network embeddings and developed an attack to recover removed node information.
result Significant information about removed node's neighbors can be retrieved from remaining embeddings.
An increasing number of sensors on mobile, Internet of things (IoT), and wearable devices generate time-series measurements of physical activities. Though access to the sensory data is critical to the success of many beneficial applications such as health monitoring or activity recognition, a wide range of potentially …
The protection of user privacy is an important concern in machine learning, as evidenced by the rolling out of the General Data Protection Regulation (GDPR) in the European Union (EU) in May 2018. The GDPR is designed to give users more control over their personal data, which motivates us to explore machine learning fr…
Link prediction (LP) algorithms propose to each node a ranked list of nodes that are currently non-neighbors, as the most likely candidates for future linkage. Owing to increasing concerns about privacy, users (nodes) may prefer to keep some of their connections protected or private. Motivated by this observation, our …
TIPRDC anonymizes data features to protect privacy while retaining useful information.
problem Privacy concerns from crowdsourced data hinder deep learning applications.
method Hybrid training method combining adversarial and mutual information estimation.
result Feature extractor hides private information while preserving original data features.
Novel mean estimation method under user-level differential privacy reduces noise in continual mean estimates.
problem Maintaining accurate running mean estimates under user-level differential privacy.
method Developed a novel mean estimation specific factorization under approximate differential privacy.
result Achieved asymptotically lower mean-squared error bounds in continual mean estimation.
A new constructivist approach to modeling in economics and theory of consciousness is proposed. The state of elementary object is defined as a set of its measurable consumer properties. A proprietor's refusal or consent for the offered transaction is considered as a result of elementary economic measurement. We were al…
Study differential privacy in multi-agent RL, achieving efficient and private learning.
problem Protecting sensitive data in multi-agent reinforcement learning.
method Extending DP definitions to two-player games, designing an efficient algorithm with privatized bonuses.
result Achieved trajectory-wise differential privacy in multi-agent RL, improving regret bounds.
A new federated learning method protects privacy in mobile crowdsensing.
problem Data and model privacy protection in federated extreme gradient boosting for mobile crowdsensing.
method Secret sharing based federated learning architecture FedXGB.
result FedXGB achieves less than 1% accuracy loss while preserving model privacy.
DPConvCNP learns to predict private data accurately and privately.
problem Balancing privacy and accuracy in machine learning models.
method Meta-learning combined with improved DP mechanism.
result DPConvCNP outperforms DP GP baseline, especially on non-Gaussian data.
We summarize the potential impact that the European Union's new General Data Protection Regulation will have on the routine use of machine learning algorithms. Slated to take effect as law across the EU in 2018, it will restrict automated individual decision-making (that is, algorithms that make decisions based on user…
Issues regarding explainable AI involve four components: users, laws & regulations, explanations and algorithms. Together these components provide a context in which explanation methods can be evaluated regarding their adequacy. The goal of this chapter is to bridge the gap between expert users and lay users. Different…
Local differential privacy method protects image privacy in machine learning.
problem Protecting image privacy in machine learning models from data owners.
method Locally perturbs image representations before releasing them to the data user.
result Proposes DCAConv, an image feature extractor that maintains high data utility while preserving privacy.
Information retrieval (IR) systems often leverage query data to suggest relevant items to users. This introduces the possibility of unfairness if the query (i.e., input) and the resulting recommendations unintentionally correlate with latent factors that are protected variables (e.g., race, gender, and age). For instan…
Paper proposes a method to encrypt faces while maintaining visual similarity.
problem Protecting personal data from unauthorized face recognition.
method Targeted identity-protection iterative method (TIP-IM) to generate adversarial identity masks.
result TIP-IM provides 95%+ protection success rate against face recognition models.
A new federated learning method clusters users into multiple models for better data distribution handling.
problem Non-IID data from heterogeneous sources in federated learning.
method Proposes a multi-center aggregation mechanism to learn multiple global models and optimally match users to centers.
result Our method outperforms existing federated learning methods on benchmark datasets.