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.
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. 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.
Model explanations can leak sensitive training data information, posing privacy risks.
problem Privacy risks of model explanations that expose training data information.
method Membership inference attacks on feature-based model explanations.
result Backpropagation-based explanations reveal statistical information about decision boundaries, leaking training data membership.
Smooth calibration improves forecast reliability even with leaked information.
problem Improving forecast reliability with leaked information.
method Combining nearby forecasts to ensure smooth calibration, which can be guaranteed by deterministic procedures.
result Smooth calibration can be guaranteed by deterministic procedures even with leaked forecasts, and it yields uncoupled finite-memory dynamics in games.
Two deep learning models predict protein-protein interactions with high accuracy.
problem Overfitting and information leak in deep learning models for PPI prediction.
method Carefully designed deep learning models, strict conditions for training and testing, and methodology to avoid information leak.
result Best model predicts more than 78% of human PPI with strong confidence.
This paper investigates the effect of leak in spiking neural networks.
problem Comparative analysis of leaky and non-leaky spiking neuron models.
method Experimental and frequency domain analysis of spiking neural networks.
result Leaky spiking neuron models provide improved robustness and generalization but decrease sparsity of computation.
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.
Develops DP-SCD for stochastic coordinate descent, making it differentially private.
problem Privacy leak in auxiliary information during stochastic coordinate descent training.
method Develops DP-SCD, leveraging independent noise addition and decoupling/parallelizing coordinate updates.
result Demonstrates competitive performance against DP-SGD with less tuning.
Deep RL policies can leak private information from trained policies.
problem Privacy leakage in deep reinforcement learning models.
method Environment dynamics search via genetic algorithm and candidate inference based on shadow policies.
result 95.83% average recovery rate of floor plans from trained Grid World navigation DRL agents.
Paper evaluates and improves private feature selection methods.
problem Feature selection in high-dimensional datasets with privacy constraints.
method Correlations-based order statistic privatized for feature selection.
result Our method significantly outperforms established baseline for private feature selection.
This paper studies trade-offs in private prediction methods.
problem Leakage of training data information in machine learning predictions.
method Private training and private prediction methods with trade-offs.
result Private training methods outperform private prediction methods in various settings.
Fault diagnosis method for refrigerant leaks using scaling law.
problem Difficulty in improving fault-detection model generalization due to complex system configuration and insufficient data.
method Derive a scaling law based on physical modeling and control mechanism, apply to other systems without modification.
result Scaling exponents of different air-conditioning systems are equivalent, indicating the proposed method's applicability.
Differentially private algorithms protect model explanations from leaking training data.
problem Model explanations can leak training data, compromising privacy.
method Adaptive differentially private gradient descent algorithm to produce accurate, private explanations.
result Privacy amplification and reduction of overall privacy loss on explanation data.
Study reveals how machine translation models can leak data privacy.
problem Detecting if a specific data sample was used to train machine translation models.
method Defined membership inference problem for sequence-to-sequence models, tested on machine translation models.
result Machine translation models can leak private information about training data.
Multi-task learning (MTL) refers to the paradigm of learning multiple related tasks together. In contrast, in single-task learning (STL) each individual task is learned independently. MTL often leads to better trained models because they can leverage the commonalities among related tasks. However, because MTL algorithm…
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.
DIET-SNN optimizes SNNs for faster, lower-energy image classification.
problem High inference latency and inefficient input encoding in SNNs.
method End-to-end backpropagation to optimize membrane leak and firing threshold.
result Achieves top-1 accuracy of 69% on ImageNet with 5 timesteps and 12x less compute energy.
New attacks reveal dataset changes in online learning models.
problem Data leakage in online learning models after updates.
method Encoder-decoder formulation, hybrid generative model (CBM-GAN).
result Proposed attacks achieve strong performance in inferring updating set information.
Paper analyzes privacy risks of learning complex models.
problem Privacy leakage from learning high-dimensional graphical models.
method Theoretical analysis of tracing attacks on Bayesian networks.
result Provides a tight upper bound on tracing attack power.
Paper shows Cox model optimisation leaks patient data in distributed learning.
problem Risk of patient data leakage in distributed learning models.
method Optimisation of Cox survival model using federated learning.
result Optimisation process can leak patient data, necessitating new validation methods.
Semi-supervised method predicts faults in systems with multiple operation modes.
problem Fault detection in industrial systems with missing target data.
method Semi-supervised soft sensor modeling incorporating mode transition properties.
result Regression coefficients estimated under constraint conditions from mode transitions.
In machine learning (ML) security, attacks like evasion, model stealing or membership inference are generally studied in individually. Previous work has also shown a relationship between some attacks and decision function curvature of the targeted model. Consequently, we study an ML model allowing direct control over t…
Improved differentially private drug sensitivity prediction using compact representations.
problem Challenges in differentially private machine learning with genomic data.
method Representation learning using variational autoencoders, PCA, and random projection.
result Variational autoencoders provide the most accurate predictions for differentially private drug sensitivity prediction.
Average-case information complexity for learning is bounded, revealing only O(d) bits for most concepts.
problem Understanding the average-case information leakage in learning algorithms for concept classes.
method Developed a learning algorithm that reveals O(d) bits of information for most concepts in a class of VC-dimension d.
result Most concepts in the class do not require large amounts of information leakage, revealing only O(d) bits on average.
Proposes QNN to protect input privacy in neural networks.
problem Protecting input privacy in neural networks.
method Quaternion-valued neural network (QNN) to hide input information.
result QNN effectively protects input privacy without significant accuracy loss.
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.
First differentially private off-policy evaluation method.
problem Privacy leakage in reinforcement learning using sensitive data.
method Differential privacy approach for off-policy evaluation.
result Empirically outperforms previous methods in speed of convergence.
A new property fixes look-ahead bias in backtesting and trading pipelines.
problem Fixing look-ahead bias in backtesting and trading pipelines.
method Developed a pipeline calculus separating availability from reference time, and a type-and-effect system for the value-independent fragment.
result The check scales linearly and catches all leaks, including those missed by differential and tiling detectors.
The issue of giving an explicit description of the flow of information concerning the time of bankruptcy of a company (or a state) arriving on the market is tackled by defining a bridge process starting from zero and conditioned to be equal to zero when the default occurs. This enables to catch some empirical facts on …
DarkneTZ protects edge devices from DNN model leaks using TEE and model partitioning.
problem Privacy risks of pre-trained DNNs on edge devices through membership inference attacks.
method Model partitioning into sensitive and untrusted parts, leveraging TEE.
result DarkneTZ provides reliable model privacy with minimal performance overhead.
New framework predicts earnings announcements using press release content, surpassing earnings surprises.
problem Predicting stock returns based on earnings press releases.
method Compared traditional and BERT-based embeddings of press releases, finding content as informative as earnings surprises.
result FinBERT yields highest predictive power for earnings announcement returns.
Optimizes privacy vs. utility trade-off through optimal transport.
problem Balancing privacy and utility in strategic information.
method Formalizes as an optimization problem with regularization, using Sinkhorn loss.
result The Sinkhorn loss naturally emerges, making the problem efficiently solvable.
New method bounds membership inference attack success using mutual information.
problem Vulnerability of deep neural networks to membership inference attacks.
method Extended Fano's inequality to measure mutual information between inputs and activations.
result Empirical evaluation shows strong correlation between mutual information and model susceptibility.
LEAK learns from mistakes to improve point cloud segmentation.
problem Improving point cloud semantic segmentation performance.
method Coarse-to-fine clustering, class-conditional prototypical feature alignment, fairness weighting.
result State-of-the-art performances on different architectures, datasets, and tasks.
Bayesian approach quantifies uncertainty in LLM evaluations.
problem Statistical uncertainty in evaluating LLM behavior.
method Bayesian evaluation of LLM behavior using probabilistic text generation strategies.
result Bayesian approach provides useful uncertainty quantification about LLM behavior.
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 framework for partially encrypted machine learning using functional encryption.
problem Performing machine learning on encrypted data without revealing sensitive information.
method Combining adversarial training and functional encryption to efficiently compute quadratic functions and prevent feature leakage.
result The proposed framework maintains high model accuracy while significantly improving data privacy.
A collaborative machine teaching method that improves learner performance with privacy and efficiency.
problem Improving learner performance with distributed teachers while maintaining privacy and scalability.
method Formulates collaborative teaching as a consensus and privacy-preserving optimization process to minimize teaching risk.
result The proposed method delivers significantly more accurate teaching results with high speed compared to non-collaborative MINLP-based super teaching.
Graph embedding leaks sensitive graph properties and subgraphs.
problem Privacy risks in graph embedding sharing.
method Three inference attacks and a defense mechanism.
result High accuracy in inferring graph properties and subgraphs.
RENNs protect input privacy by rotating d-ary features.
problem Protecting input privacy from intermediate-layer features.
method Rotation-equivariant neural networks using d-ary vectors/tensors.
result RENNs effectively hide input information without degrading output accuracy.
Proposes a privacy-preserving method for graph embedding.
problem Privacy leakage in adjacency spectral embedding for stochastic blockmodels.
method Differentially private adjacency spectral embedding algorithm for stochastic blockmodels.
result Estimates latent positions close to those by non-private embedding, maintaining accuracy at desired privacy levels.
Fidel-TS creates a new benchmark for time series forecasting models.
problem Lack of high-quality benchmarks for time series forecasting models.
method Formalized high-fidelity benchmark principles, including data sourcing integrity, leak-free design, and structural clarity. Created Fidel-TS, a new large-scale benchmark.
result Demonstrated the limitations of prior benchmarks and potential discrepancies in model evaluation.
ZDP detects drift in large language models without labels, proving key theorems and metrics.
problem Detecting drift in large language models without task labels or output evaluations.
method Zero-Direction Probing (ZDP) framework based on null directions of transformer activations, proving theoretical guarantees.
result Proves the Variance--Leak Theorem, Fisher Null-Conservation, Rank--Leak bound, and logarithmic-regret guarantee.
Proposes a privacy-preserving recommendation system using matrix factorization and differential privacy.
problem Privacy leakage in recommendation systems when anonymizing user data is not sufficient.
method Uses matrix factorization and differential privacy via the Gaussian mechanism.
result Demonstrates excellent utility for privacy-preserving recommendation systems.
The paper proposes selective forgetting for deep neural networks at a finer level than samples.
problem Selective forgetting of deep neural networks to handle outliers, poisoned data, or sensitive information.
method Formulated selective forgetting at a finer level than samples, introduced as an optimization problem on three criteria.
result Experimental results show the model can forget specific information for classification, improving accuracy in specific cases.
Paper reconstructs training data from a single gradient query.
problem Privacy threats in federated learning due to model gradients.
method Provable attack using tensor decomposition.
result Training samples can be fully reconstructed from a single gradient query.
A new framework for mobile authentication using deep metric learning.
problem Challenges in mobile authentication using behavioral biometrics.
method Deep metric learning, private data protection, flexible training scheduling.
result 95% authentication accuracy on public datasets, robust against attacks.