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.
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.
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.
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.
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.
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.
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.
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.
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 …
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.
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…
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…
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.
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.
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…
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.
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.
Green bond leaks impact equity markets, altering investor reactions.
problem Green bond leaks affect equity market reactions.
method Identified 259 instances of pre-announcement leaks in 2,036 green bond headlines.
result News leaks significantly alter equity trading dynamics and investor reactions.
ForesightFlow detects informed trading on prediction markets using an information leakage score.
problem Detecting informed trading on decentralized prediction markets.
method Developed an Information Leakage Score (ILS) framework to quantify the fraction of terminal information move priced in before public news events.
result The score connects label generation to proper-scoring-rule literature and reveals systematic biases in insider trading documentation.
There is an increasing concern that most current published research findings are false. The main cause seems to lie in the fundamental disconnection between theory and practice in data analysis. While the former typically relies on statistical independence, the latter is an inherently adaptive process: new hypotheses a…
Powered by machine learning services in the cloud, numerous learning-driven mobile applications are gaining popularity in the market. As deep learning tasks are mostly computation-intensive, it has become a trend to process raw data on devices and send the deep neural network (DNN) features to the cloud, where the feat…
Study evaluates information leakage in Polymarket markets, finding limited applicability and resolution ambiguity.
problem Limited applicability of ILS-dl framework across Polymarket markets.
method Scaling from single-case to population-scale evaluation using ILS-dl framework.
result Only 0.7% of candidate markets yield computable ILS-dl values, and resolution semantics are the main obstacle.
Strategic brokers exploit private information in broker-mediated markets, affecting informed traders' performance.
problem Strategic interactions and information leakage in broker-mediated markets.
method Study of strategic trading behavior and information leakage in a broker-mediated market.
result Brokers hold a strategic advantage over informed traders due to information leakage in trading flows.
Study on privacy leakage in noisy gradient descent algorithms.
problem Information leakage of iterative randomized learning algorithms about training data.
method Analyzes the dynamics of Rényi differential privacy loss in noisy gradient descent algorithms.
result Privacy loss converges exponentially fast for smooth and strongly convex loss functions.
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.
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.
In this paper, we aim to understand the generalization properties of generative adversarial networks (GANs) from a new perspective of privacy protection. Theoretically, we prove that a differentially private learning algorithm used for training the GAN does not overfit to a certain degree, i.e., the generalization gap …
Bayesian deep learning is recently regarded as an intrinsic way to characterize the weight uncertainty of deep neural networks~(DNNs). Stochastic Gradient Langevin Dynamics~(SGLD) is an effective method to enable Bayesian deep learning on large-scale datasets. Previous theoretical studies have shown various appealing p…
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…
Privacy improves robustness in statistical estimation.
problem Sparse mean estimation under privacy constraints.
method Sum-of-Squares method and exponential-time mechanisms.
result Private algorithms matching optimal tradeoffs are not known, but achieved via Sum-of-Squares.
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.
Paper proposes a new ML approach to estimate g-vulnerability without estimating conditional probabilities.
problem Estimating information leakage in black-box systems with large output domains.
method Developed a novel ML-based approach to estimate g-vulnerability without estimating conditional probabilities.
result The proposed method outperforms frequentist approach when dealing with large output domains.
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.
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.
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.
Machine learning services pose privacy risks if data or model parameters are compromised.
problem Privacy risks in machine learning services when data or model parameters are exposed.
method Systematic review of privacy challenges, adversarial models, attacks, and defenses.
result Need for better evaluations, targeted defenses, and policy studies.
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…
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…
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.
DPNR preserves privacy of text representations using differential privacy.
problem Privacy leakage in deep learning text representations.
method DPNR uses Differential Privacy to provide formal privacy guarantees and dropout masking for enhanced privacy.
result DPNR reduces privacy leakage without significantly sacrificing main task performance.
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.
Paper evaluates deadline-ILS on insider trading contracts, finding it distinguishes signals from noise.
problem Deadlines in insider trading contracts and information leakage detection.
method Empirical evaluation using FFIC dataset, hazard-rate estimation, cross-market wallet analysis.
result Deadline-ILS distinguishes signal from proxy artefact, with a significant shift in magnitude.
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.
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…
Models leak information about their training data. This enables attackers to infer sensitive information about their training sets, notably determine if a data sample was part of the model's training set. The existing works empirically show the possibility of these membership inference (tracing) attacks against complex…