New approach detects sensitive info in text, outperforming previous methods.
problem Detecting sensitive information in unstructured text documents.
method Developed novel recursive neural network approaches for sensitive info detection, assuming only labeled examples.
result Our approaches significantly outperform previous keyword-based methods on real-world data.
TaCo prevents non-linear classifiers from detecting sensitive attributes.
problem Ensuring fairness in NLP models by preventing sensitive attribute detection.
method Targeted Concept Erasure (TaCo) removes sensitive information from final latent representations, even against non-linear classifiers.
result TaCo outperforms state-of-the-art methods in reducing sensitive attribute prediction accuracy while preserving overall task performance.
New method explains sensitivity of test data uncertainty in Bayesian inference.
problem Widespread belief that test data similarity reduces epistemic uncertainty.
method Information-theoretic decomposition of predictive uncertainty.
result Defines sensitivity using information-theoretic quantities.
Proposes a method to improve surrogate models by incorporating sensitivity information.
problem Pruned neural networks often fail to capture sensitivities and uncertainties of original models.
method Combines Interval Adjoint Significance Analysis and Sobolev Training to accurately model sensitivities.
result Pruned models based on the proposed method better match original sensitivities.
Optimizes portfolios using neural network approximations of asset sensitivities to common drivers.
problem Optimizing portfolios with complex asset dynamics and common drivers.
method Model asset dynamics with PDEs, approximate sensitivities with neural networks, and use hierarchical clustering on sensitivity matrix for optimization.
result Achieves over-performance in portfolio optimization across various markets and datasets.
The paper analyzes binary option markets with exogenous information and price sensitivity.
problem Analyzing binary option markets with exogenous information and price sensitivity.
method Derive and analyze a continuous model of binary option markets with exogenous information, using Filippov surfaces and general assumptions on purchasing rules.
result Price always converges when exogenous information is constant, and price sensitivity affects price lag vs. information.
Proposes fair classification method using Wasserstein-1 distances.
problem Ensuring fairness in classification models by protecting sensitive information.
method Minimizes Wasserstein-1 distances to enforce independence between classifier outputs and sensitive information.
result Empirical performance superior to fairness baselines on benchmark datasets.
A central goal of algorithmic fairness is to reduce bias in automated decision making. An unavoidable tension exists between accuracy gains obtained by using sensitive information (e.g., gender or ethnic group) as part of a statistical model, and any commitment to protect these characteristics. Often, due to biases pre…
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.
New method mitigates bias without sensitive data using causal graph and variational autoencoder.
problem Lack of fairness strategies when sensitive attributes are not collected.
method SRCVAE framework based on causal graph for inferring a proxy sensitive attribute.
result Significant improvements in fairness metrics over existing methods.
Develops a method to ensure fairness across multiple sensitive attributes in machine learning.
problem Ensuring fairness among demographic groups formed by multiple sensitive attributes.
method Formulates intersectional fairness as a mutual information minimization problem and proposes a generic end-to-end algorithmic framework.
result Demonstrates effective debiasing of classification results with minimal impact to accuracy.
New method protects sensitive data in deep learning training.
problem Protecting sensitive data in deep learning training.
method Distributed layer-partitioned training with step-wise activation functions.
result Experimental results show the method is simple and effective.
We introduce the BriarPatch, a pixel-space intervention that obscures sensitive attributes from representations encoded in pre-trained classifiers. The patches encourage internal model representations not to encode sensitive information, which has the effect of pushing downstream predictors towards exhibiting demograph…
We present and evaluate Deep Private-Feature Extractor (DPFE), a deep model which is trained and evaluated based on information theoretic constraints. Using the selective exchange of information between a user's device and a service provider, DPFE enables the user to prevent certain sensitive information from being sha…
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 framework improves fairness in machine learning models.
problem Eliminating discrimination in machine learning models for sensitive fields.
method Reformulate data input by removing sensitive features and design adversarial network to minimize dependence.
result Our model achieves better fairness metrics and prediction performance than state-of-the-art methods.
Study risk-sensitive RL in offline settings, improving efficiency and accuracy.
problem Efficiently derive near-optimal policies for risk-sensitive RL using offline data.
method Introduced two provably sample-efficient algorithms for risk-sensitive offline RL in linear MDPs.
result First provably efficient risk-sensitive offline RL algorithms.
Develops a method to explain deep learning models for complex systems.
problem Rapid simulation-based prototyping of complex systems with high-dimensional CVs and QoIs.
method Moment-independent global sensitivity analysis using differential mutual information.
result Surrogate model driven by mutual information provides useful rankings and optimizations.
Cost-Sensitive Online Classification has drawn extensive attention in recent years, where the main approach is to directly online optimize two well-known cost-sensitive metrics: (i) weighted sum of sensitivity and specificity; (ii) weighted misclassification cost. However, previous existing methods only considered firs…
This work proposes a novel privacy-preserving method for synthetic replacement of sensitive data.
problem Privacy-preserving transformations of sensitive data.
method Adversarial representation learning for synthetic replacement of private attributes.
result Our method provides stronger privacy and better utility than previous methods.
A new method for survival analysis models that ensures fairness without using sensitive demographic data.
problem Ensuring fairness in survival analysis models without relying on sensitive demographic information.
method A worst-case error minimization approach using a training loss function that does not know sensitive demographic information.
result The proposed method often scores better on fairness metrics without a significant drop in prediction accuracy compared to baselines.
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.
Paper proposes a privacy-preserving DML framework using local randomization and ADMM perturbation.
problem Privacy concerns in distributed machine learning with sensitive user data.
method Local randomization and ADMM perturbation to provide differential privacy and heterogeneous privacy levels.
result The framework minimizes privacy losses and maintains model generalization.
Label embedding (LE) is an important family of multi-label classification algorithms that digest the label information jointly for better performance. Different real-world applications evaluate performance by different cost functions of interest. Current LE algorithms often aim to optimize one specific cost function, b…
Transformers for binary decisions are sensitive to evidence order, leading to unreliable outcomes.
problem Order sensitivity in Transformers for binary decisions leads to unreliable outcomes.
method Formalized an expectation-realization gap and developed QMV and EDFL bounds.
result Uniform permutation mixtures reduce dispersion and improve reliability.
Efficiently identifies key input variables for expensive functions using active learning.
problem Efficiently identify key input variables for expensive, black-box functions.
method Proposes novel active learning acquisition functions targeting derivative-based global sensitivity measures (DGSMs) under Gaussian process surrogate models.
result Active learning substantially enhances sample efficiency of DGSM estimation, especially with limited evaluation budgets.
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.
A method improves capsule networks by reducing information dilution and enhancing performance.
problem Capsule networks struggle with datasets containing background and complex objects.
method Restrict the activation values of primary capsule layers to highlight discriminative capsules.
result The method achieves better performance on various datasets.
Paper proposes a framework to identify and obfuscate sensitive features via information density estimation.
problem Identifying and protecting sensitive attributes from leakage in obfuscation mechanisms.
method Information density estimation to identify leaking features, followed by a targeted obfuscation mechanism.
result Proven leakage guarantee in terms of Eγ-divergence for the obfuscation mechanism. A privacy-preserving method for transmitting data over a wiretap channel using generative networks.
problem Privacy protection in communication over a wiretap channel.
method Data-driven approach using variational autoencoder (VAE)-based joint source channel coding (JSCC).
result The approach provides high reconstruction quality at the receiver while confusing the eavesdropper about the latent sensitive attribute.
The paper develops a filtering framework for estimating hazard rates with jumps in financial and insurance applications.
problem Estimating hazard rates with unobservable change-points in financial and insurance contexts.
method Continuous-time filtering framework using progressive enlargement of filtration, stochastic differential equations, and sensitivity analysis.
result Explicit formula for survival probability conditional on partial information.
A framework for sensitivity measures using scoring functions.
problem Constructing sensitivity measures for any elicitable functional.
method Score-based sensitivities constructed via consistent scoring functions.
result Demonstrated intuitive and desirable properties of score-based sensitivities.
Package provides sensitivity analysis for neural networks.
problem Understanding how input variables affect neural network predictions.
method Partial derivatives method to calculate sensitivities.
result Allows evaluation of variable importance and input-output relationships.
New technique reduces bias in DNN models without sensitive attribute annotations.
problem Existing bias mitigation methods require instance-level annotations and do not guarantee removal of all sensitive information.
method Representation Neutralization for Fairness (RNF) debiases only the classification head of DNN models using neutralized representations.
result RNF effectively reduces discrimination of DNN models with minimal performance degradation.
This research assesses uncertainty quantification and sensitivity analysis for DTs in nuclear fuel performance.
problem Understanding the reliability and performance of advanced nuclear fuels using DTs.
method Introduces ML-based uncertainty quantification and sensitivity analysis methods applied to BISON fuel performance code.
result Demonstrates the effectiveness of DTs in multi-criteria decision-making for nuclear fuel performance.
Proposes a new model to identify unknown counterfactual outcomes for continuous variables.
problem Counterfactual inference for continuous outcomes with strong assumptions.
method Curvature Sensitivity Model to relax assumptions and provide informative bounds.
result Demonstrates effectiveness of the Curvature Sensitivity Model in identifying counterfactual outcomes.
Motivation: Human genomic datasets often contain sensitive information that limits use and sharing of the data. In particular, simple anonymisation strategies fail to provide sufficient level of protection for genomic data, because the data are inherently identifiable. Differentially private machine learning can help b…
EXOC framework uses auxiliary variables for counterfactual fairness in machine learning.
problem Balancing fairness and predictive accuracy in models with sensitive attributes.
method EXOC framework uses auxiliary variables to define an auxiliary node and a control node for counterfactual fairness.
result EXOC framework outperforms state-of-the-art approaches in achieving counterfactual fairness.
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.
Adaptive truncation improves privacy in online Bayesian estimation.
problem Ensuring privacy in online Bayesian estimation of a static parameter.
method Sequential Monte Carlo, adaptive truncation, Thompson sampling.
result Adaptive truncation reduces privacy-preserving noise, enabling more accurate estimation.
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.
As financial instruments grow in complexity more and more information is neglected by risk optimization practices. This brings down a curtain of opacity on the origination of risk, that has been one of the main culprits in the 2007-2008 global financial crisis. We discuss how the loss of transparency may be quantified …
Label space expansion for multi-label classification (MLC) is a methodology that encodes the original label vectors to higher dimensional codes before training and decodes the predicted codes back to the label vectors during testing. The methodology has been demonstrated to improve the performance of MLC algorithms whe…
Many reinforcement learning applications involve the use of data that is sensitive, such as medical records of patients or financial information. However, most current reinforcement learning methods can leak information contained within the (possibly sensitive) data on which they are trained. To address this problem, w…
Develops LSH schemes for f-divergences and mutual information loss.
problem Approximating nearest neighbors in high-dimensional probability distributions.
method General framework and specific LSH schemes for f-divergences and mutual information loss.
result Generalized Jensen-Shannon divergence can be approximated by Hellinger distance.
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.
The paper shows how to use proxy attributes for fairness in machine learning models with missing sensitive group data.
problem Measuring and enforcing fairness in machine learning models with incomplete sensitive group data.
method Using proxy-sensitive attributes to derive upper bounds on multiaccuracy and multicalibration violations and adjust models to satisfy these fairness notions.
result Provable upper bounds on multiaccuracy and multicalibration violations can be derived using proxy-sensitive attributes in the absence of sensitive group data.
In this paper incomplete-information models are developed for the pricing of securities in a stochastic interest rate setting. In particular we consider credit-risky assets that may include random recovery upon default. The market filtration is generated by a collection of information processes associated with economic…