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.
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.
Crowdsourced data used in machine learning services might carry sensitive information about attributes that users do not want to share. Various methods have been proposed to minimize the potential information leakage of sensitive attributes while maximizing the task accuracy. However, little is known about the theory b…
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.
MAPPING debiases GNNs for fair node classification with limited leakage.
problem Graph Neural Networks inherit and exacerbate historical discrimination in high-stake domains.
method MAPPING uses distance covariance-based fairness constraints and adversarial debiasing.
result MAPPING achieves better trade-offs between fairness and utility, mitigating privacy risks.
Image recognition systems have demonstrated tremendous progress over the past few decades thanks, in part, to our ability of learning compact and robust representations of images. As we witness the wide spread adoption of these systems, it is imperative to consider the problem of unintended leakage of information from …
Paper defends sensitive attributes in GNNs from inference attacks.
problem Protecting sensitive attributes in GNNs from inference attacks.
method Proposes adversarial training with TV and Wasserstein distance to locally filter sensitive attributes.
result Framework creates strong defense against inference attacks with minimal performance loss.
Benchmark evaluates LLM trading agents by masking identifiers to prevent memory leaks.
problem Evaluate LLM trading agents without relying on market memory or noise.
method Data-side masking protocol, Barra-style performance attribution framework.
result LLM agents' returns are largely explained by market and style exposure, not stock selection.
Researchers found PP-GANs can hide sensitive data in sanitized images, undermining privacy checks.
problem Lack of formal proofs of privacy in PP-GANs for image sanitization.
method Subverted PP-GANs for facial expression recognition to hide sensitive data in sanitized images.
result It is possible to hide sensitive identification data in sanitized PP-GAN output images, even allowing reconstruction of entire input images.
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.
This paper analyzes how training data can be leaked from gradients in neural networks and proposes a metric for measuring model security.
problem Training data leakage from gradients in neural networks for image classification.
method Formulated the problem as an optimisation problem for each layer, involving weights, gradients, and constraints from preceding layers.
result Attributed training data leakage to the architecture of the deep network and proposed a metric for measuring model security.
Latent factor models for recommender systems represent users and items as low dimensional vectors. Privacy risks of such systems have previously been studied mostly in the context of recovery of personal information in the form of usage records from the training data. However, the user representations themselves may be…
Federated learning leaks participant dataset quality even with secure aggregation.
problem Leakage of participant dataset quality in federated learning with secure aggregation.
method Image recognition experiments to infer and attribute dataset quality.
result Relative quality ordering of participants can be inferred and used for various purposes.
This paper investigates the so-called leakage effect of trading strategies generated functionally from rank-dependent portfolio generating functions. This effect measures the loss in wealth of trading strategies due to renewing the portfolio constituent stocks. Theoretically, the leakage effect of a trading strategy is…
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.
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.
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.
Machine learning models have been shown to be vulnerable to membership inference attacks, i.e., inferring whether individuals' data have been used for training models. The lack of understanding about factors contributing success of these attacks motivates the need for modelling membership information leakage using info…
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.
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.
It has been widely understood that differential privacy (DP) can guarantee rigorous privacy against adversaries with arbitrary prior knowledge. However, recent studies demonstrate that this may not be true for correlated data, and indicate that three factors could influence privacy leakage: the data correlation pattern…
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.
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.
Identifying features that leak information about sensitive attributes is a key challenge in the design of information obfuscation mechanisms. In this paper, we propose a framework to identify information-leaking features via information density estimation. Here, features whose information densities exceed a pre-defined…
Unified framework analyzes privacy risks from gradients in distributed learning.
problem Analyzing inference privacy risks from gradients in machine learning.
method Unified game-based framework for various attacks, including attribute, property, distributional, and user disclosures.
result Demonstrates inefficacy of data aggregation for privacy against inference attacks.
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.
Exchanging gradients is a widely used method in modern multi-node machine learning system (e.g., distributed training, collaborative learning). For a long time, people believed that gradients are safe to share: i.e., the training data will not be leaked by gradient exchange. However, we show that it is possible to obta…
To continuously improve quality and reflect changes in data, machine learning applications have to regularly retrain and update their core models. We show that a differential analysis of language model snapshots before and after an update can reveal a surprising amount of detailed information about changes in the train…
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.
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.
We decompose the squared price-of-risk premium into three components: intervention-stable premium, confounding wedge, and information loss.
problem Decomposing the squared price-of-risk premium into its components
method Identifying an order-three obstruction to aggregation across portfolios
result The decomposition is estimable and detectable with a permutation-calibrated screen
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.
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 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.
Face recognition models can be inferred from student models, posing privacy risks.
problem Privacy threats in transfer learning models for face recognition.
method Membership inference attacks and attribute inference from aggregate-level information.
result Sensitive attributes can be inferred from student models, even with limited auxiliary information.
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.
Underwater gas reservoirs are used in many situations. In particular, Carbon Capture and Storage (CCS) facilities that are currently being developed intend to store greenhouse gases inside geological formations in the deep sea. In these formations, however, the gas might percolate, leaking back to the water and eventua…
Deep Learning algorithms have recently become the de-facto paradigm for various prediction problems, which include many privacy-preserving applications like online medical image analysis. Presumably, the privacy of data in a deep learning system is a serious concern. There have been several efforts to analyze and explo…
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.
We consider membership inference attacks, one of the main privacy issues in machine learning. These recently developed attacks have been proven successful in determining, with confidence better than a random guess, whether a given sample belongs to the dataset on which the attacked machine learning model was trained. S…
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.