The paper analyzes generalization of noisy, iterative algorithms using maximal leakage.
problem Analyzing the generalization behavior of noisy, iterative learning algorithms.
method Information-theoretic framework with maximal leakage metric.
result Explicit upper bounds on maximal leakage for various scenarios.
New approach to adaptive data analysis via maximal leakage, improving statistical guarantees.
problem False findings in published research due to disconnection between theory and practice in data analysis.
method Introduces Maximal Leakage, an information-theoretic measure, to compare adaptivity with non-adaptivity.
result Generalizes statistical guarantees for adaptive contexts, improving or replicating existing results.
Develops a framework to obfuscate sensitive attributes in machine learning models.
problem Minimizing information leakage of sensitive attributes in crowdsourced data.
method Proposes a minimax optimization formulation and proves an information-theoretic lower bound.
result Adversarial learning achieves the best trade-off between attribute obfuscation and accuracy.
New defense method protects client data privacy in federated learning.
problem Gradient leakage attacks in federated learning.
method Learning to obscure data to generate synthetic samples.
result Synthetic samples preserve predictive features and protect privacy.
Improved canary crafting for one-run privacy auditing reduces leakage estimates.
problem Detecting canaries in one-run privacy auditing to estimate leakage effectively.
method Optimizes canaries for detectability and diversity, using a greedy initialization and bilevel optimization.
result Achieves stronger leakage estimates at lower computational cost.
New framework quantifies and reduces concept-based models' leakage.
problem Information leakage in concept-based models reduces interpretability.
method Information-theoretic framework with CTL and ICL measures.
result Measures predict model behaviour and identify leakage causes.
The paper examines how trading strategies lose value due to stock turnover.
problem Leakage of rank-dependent trading strategies due to stock turnover.
method Theoretical analysis and empirical estimation of leakage in discrete time.
result A new method to estimate leakage in trading strategies is introduced.
bioLeak addresses data leakage in biomedical machine learning studies.
problem Data leakage causes optimistic bias in machine learning models for biomedical studies.
method bioLeak provides leakage-aware resampling workflows and model audits in R.
result The package supports various machine learning tasks and can detect leakage mechanisms.
In this paper, we focus on finding clusters in partially categorized data sets. We propose a semi-supervised version of Gaussian mixture model, called C3L, which retrieves natural subgroups of given categories. In contrast to other semi-supervised models, C3L is parametrized by user-defined leakage level, which control…
This paper bounds min-entropy leakage for Blowfish privacy using graph symmetries.
problem Bounding min-entropy leakage for Blowfish privacy mechanisms.
method Organizing analysis over symmetrical partitions corresponding to orbits of graph automorphism groups.
result Demonstrates a construction meeting the bound with asymptotic equality, showing tightness.
Deep Leakage from Gradients can reveal private training data from shared gradients.
problem The safety of gradients in multi-node machine learning systems is questionable.
method Empirical validation of Deep Leakage from Gradient attack on computer vision and natural language processing tasks.
result The attack is more effective than previous methods, achieving pixel-wise accuracy for images and token-wise matching for texts.
Real-time fuel leakage detection framework MOCPD improves accuracy.
problem Early detection of fuel leakage to prevent hazards and losses.
method Memory-based Online Change Point Detection (MOCPD) framework.
result MOCPD outperforms baseline methods in detection accuracy.
Unified analysis of privacy leakage in correlated data considering prior knowledge.
problem Understanding the impact of prior knowledge and data correlation on privacy leakage.
method Proposed prior differential privacy (PDP) and analyzed using WHG and multivariate Gaussian models.
result Derived closed-form expression for continuous data and chain rule for discrete data.
New model quantifies how much machine learning models can reveal about individual data usage.
problem Measuring and reducing the leakage of membership information from machine learning models.
method Using information theory, conditional mutual information leakage, and Kullback-Leibler divergence to quantify and bound the leakage.
result The amount of membership information leakage is reduced by adding Gaussian (ε,δ)-differentially-private additive noises. Differential privacy protects data privacy by adding noise to data.
problem Leakage of sensitive data through common methods like encryption and endpoint protection.
method Randomized response technique to add noise to data collection.
result Differential privacy ensures strong privacy with better utility.
This paper evaluates and compares gradient leakage attacks in federated learning.
problem Gradient leakage attacks compromise client privacy in federated learning.
method Formal and experimental analysis of gradient leakage attacks, evaluation of attack effectiveness and cost.
result Gradient leakage attacks can reconstruct private local training data from shared parameter updates.
Reduces data leakage in distributed deep learning models.
problem Prevents reconstruction of sensitive raw data patterns during client communications.
method Reduces distance correlation between raw data and learned representations.
result Resilient to reconstruction attacks while maintaining model accuracy.
Paper tackles treatment leakage in text-based causal inference, proposing methods to mitigate bias.
problem Treatment leakage in text-as-confounder applications introduces bias in causal estimates.
method Formal definitions, four text distillation methods (passage removal, classification, salient feature removal, nullspace projection).
result Moderate distillation optimally balances bias reduction against confounder retention.
New analysis shows reconstruction attacks are unreliable without prior data knowledge.
problem Privacy and security risks from neural network memorization of training data.
method Complementary analysis of reconstruction methods, proving their unreliability without prior data knowledge.
result Reconstruction attacks are fundamentally unreliable without prior data knowledge, and networks trained more extensively are less susceptible.
The paper analyzes privacy leakage in federated learning using linear algebra and optimization theory.
problem Privacy leakage in federated learning despite its promise for data privacy.
method Theoretical analysis from linear algebra and optimization theory perspectives.
result Derives sufficient conditions to prevent data reconstruction attacks and establishes an upper bound on privacy leakage.
Synth-MIA assesses privacy leakage in synthetic tabular data models.
problem Challenges in evaluating privacy leakage in synthetic tabular data.
method Unified threat framework deploying multiple attacks.
result Higher synthetic data quality correlates with greater privacy leakage.
Analysis of model updates reveals sensitive data leaks.
problem Information leakage during model updates.
method Differential analysis of language model snapshots.
result New metrics (differential score, differential rank) reveal sensitive data leaks.
Paper mitigates information leakage in image representations using maximum entropy.
problem Mitigating unintended leakage of user information from image representations.
method Formulates an adversarial non-zero sum game to find an embedding function that maximizes task-dependent discriminative information while minimizing entropy of sensitive attributes.
result Proposed approach learns image representations with high task performance and reduced leakage of sensitive information.
Benchmark detects decision-time leakage in financial backtests.
problem Detecting decision-time leakage in financial machine-learning backtests.
method Toggles one evaluation convention at a time around a clean t+1-open reference, holding other factors fixed. result Inflation is highly selective, affecting specific features and execution methods.
Framework prevents data leakage in mobile cloud DNNs.
problem Data leakage from cloud DNNs poses privacy risks.
method Privacy-preserving reinforcement learning framework.
result Framework successfully defends against various privacy attacks.
Multi-party machine learning leaks global dataset properties even with black-box access.
problem Leakage of global dataset properties in multi-party machine learning.
method Demonstrated leakage of sensitive attribute distributions in pooled data.
result A curious party can infer sensitive attribute distributions in other parties' data with high accuracy.
Deep learning reconstructs pressure fields and classifies leakage rates in CCS storage sites.
problem Monitoring CO2 leakage in CCS storage sites.
method Variational auto-encoder tailored for pressure field reconstruction and leakage rate classification.
result Uncertainty estimates of predictions illustrated on synthetic data.
PASE method protects machine learning models from membership inference attacks without significant accuracy loss.
problem Membership inference attacks on machine learning models.
method Switching ensembles approach to mitigate privacy leakage.
result PASE method provides effective privacy protection with minimal accuracy penalty.
fastml guards against data leakage in automated machine learning.
problem Data leakage during preprocessing before resampling inflates apparent performance.
method fastml uses guarded resampling to re-estimate preprocessing inside each resample.
result Guarded resampling reduces apparent performance compared to global preprocessing.
Log-Loss scores expose membership privacy breaches.
problem Privacy leakage from statistical aggregates like Log-Loss scores.
method Proved that Log-Loss scores enable full accuracy membership inference in a single query.
result Complete membership privacy breach is possible with Log-Loss scores.
New insights link diverse statistical problems via secret leakage planted clique.
problem Statistical-computational gaps in inference problems.
method Secret leakage planted clique as a new hardness assumption for reductions.
result Establishes tight statistical-computational tradeoffs for various problems.
Machine learning confound removal biases results, leading to misleading predictions.
problem Common confound removal methods in machine learning lead to misleading predictions.
method Featurewise removal of confound variance by linear regression before applying ML.
result This common deconfounding approach can leak information, amplifying null or moderate effects.
New bounds on machine learning data leakage identified.
problem Machine Learning models can leak sensitive information.
method Formalized attack setups, derived universal bounds, studied mutual information.
result Connected attack success rate to generalization gap and mutual information.
New method detects information leakage using approximate Bayes predictor.
problem Unintentional exposure of sensitive information via observable data.
method Statistical learning theory and information theory framework, approximating Bayes predictor's log-loss and accuracy.
result MI can be accurately estimated to detect ILs, outperforming state-of-the-art baselines.
Optimal defenses protect FL models from gradient reconstruction attacks.
problem Gradient reconstruction attacks compromise FL models by recovering original data from shared gradients.
method Derive a theoretical lower bound of reconstruction error, customize noise and pruning defenses, and achieve optimal trade-off between leakage and utility.
result Our methods outperform Gradient Noise and Pruning in protecting training data and maintaining model utility.
LLM forecasting benchmarks suffer from information leakage, which confounds model performance.
problem LLM forecasting benchmarks suffer from information leakage.
method A retrieval-augmented LLM forecaster observes only decision-time information.
result The full pipeline obtains a median monthly Spearman rank IC of +0.154.
Paper explores GAN generalization via privacy protection, proving bounds on generalization gap and reducing leakage.
problem Understanding and bounding the generalization gap of GANs.
method Theoretical proof using differential privacy, reinterpreting Bayesian GAN, membership attacks.
result Proven bounds on generalization gap and reduced information leakage.
Improved forecasting in daily time series competition using a correlator method.
problem Forecasting daily time series with data leakage issues.
method Ensemble of five statistical forecasting methods and a correlator method.
result The correlator method was responsible for most of the gains over naive forecasting.
DEDACT breaks down feature importance into direct and associative components.
problem Lack of clear distinction between direct and associative feature importance.
method DEDACT framework to decompose direct and associative importance measures.
result Provides insight into sources of prediction-relevant information and feature pathways.
Machine learning detects underwater gas leaks.
problem Early detection of gas leaks in underwater reservoirs.
method Machine learning and Passive Acoustic Monitoring (PAM).
result Classification algorithms achieve good performance in detecting leaks.
SGLD protects membership privacy in Bayesian deep learning.
problem Preventing membership attack in Bayesian deep learning.
method Theoretical framework based on information leakage analysis.
result SGLD prevents information leakage to a certain extent.
This work provides bounds on generalization error and privacy leakage in federated learning.
problem Bounding generalization error and privacy leakage in federated learning.
method Information-theoretic framework for classical, distributed, and federated learning.
result Upper and lower bounds on generalization error and privacy leakage.
Paper evaluates security of deep learning from side-channel attacks.
problem Security of deep learning algorithms from side-channel attacks.
method Uses hardware performance counters to test for information leakage in CNNs.
result Shows alarms for potential data privacy breaches in CNNs.
Differential privacy of Gaussian process posterior sampling
problem Privacy of posterior sample paths from Gaussian process
method Intrinsic randomness yields DP guarantees
result Intrinsic randomness yields DP guarantees
Embeddings leak sensitive information about input data, which can be recovered or inferred.
problem Information leakage in embedding models.
method Developed three classes of attacks to study information leakage.
result Embeddings leak sensitive information about input data, which can be partially recovered or inferred.
Temporal-Difference learning (TD) [Sutton, 1988] with function approximation can converge to solutions that are worse than those obtained by Monte-Carlo regression, even in the simple case of on-policy evaluation. To increase our understanding of the problem, we investigate the issue of approximation errors in areas of…
Paper proposes incentive mechanism to encourage participation in federated learning.
problem Users are reluctant to participate in federated learning due to privacy concerns.
method Formulated as a two-stage Stackelberg game, designed an incentive mechanism to select and compensate users.
result Demonstrated effectiveness of the proposed incentive mechanism through simulations.
Enhanced Bayesian target encoding uses sampling techniques to improve model performance.
problem Improving target encoding for better model performance in machine learning.
method Using sampling techniques in Bayesian target encoding to extract intra-category distribution information.
result Improves generalization and reduces target leakage in machine learning models.