A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
This paper investigates the effect of leak in spiking neural networks.
Green bond leaks impact equity markets, altering investor reactions.
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…
Early fault detection using instrumented sensor data is one of the promising application areas of machine learning in industrial facilities. However, it is difficult to improve the generalization performance of the trained fault-detection model because of the complex system configuration in the target diagnostic system…
Embeddings leak sensitive information about input data, which can be recovered or inferred.
Smooth calibration improves forecast reliability even with leaked information.
LEAK learns from mistakes to improve point cloud segmentation.
DIET-SNN optimizes SNNs for faster, lower-energy image classification.
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…
Fidel-TS creates a new benchmark for time series forecasting models.
ZDP detects drift in large language models without labels, proving key theorems and metrics.
Differentially private algorithms protect model explanations from leaking training data.
Federated learning leaks participant dataset quality even with secure aggregation.
A new framework for mobile authentication using deep metric learning.
Paper evaluates and improves private feature selection methods.
DP-SGD analysis shows many datapoints leak less privacy than previously thought.
This paper studies trade-offs in private prediction methods.
Privacy and transparency are two key foundations of trustworthy machine learning. Model explanations offer insights into a model's decisions on input data, whereas privacy is primarily concerned with protecting information about the training data. We analyze connections between model explanations and the leakage of sen…
It is widely believed that sharing gradients will not leak private training data in distributed learning systems such as Collaborative Learning and Federated Learning, etc. Recently, Zhu et al. presented an approach which shows the possibility to obtain private training data from the publicly shared gradients. In their…
Develops DP-SCD for stochastic coordinate descent, making it differentially private.
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…
Biological data are extremely diverse, complex but also quite sparse. The recent developments in deep learning methods are offering new possibilities for the analysis of complex data. However, it is easy to be get a deep learning model that seems to have good results but is in fact either overfitting the training data …
Multi-party machine learning leaks global dataset properties even with black-box access.
DarkneTZ protects edge devices from DNN model leaks using TEE and model partitioning.
Paper shows Cox model optimisation leaks patient data in distributed learning.
New analysis shows SGD with noise doesn't leak more privacy with more iterations.
Machine learning on encrypted data has received a lot of attention thanks to recent breakthroughs in homomorphic encryption and secure multi-party computation. It allows outsourcing computation to untrusted servers without sacrificing privacy of sensitive data. We propose a practical framework to perform partially encr…
Despite the robust structure of the Internet, it is still susceptible to disruptive routing updates that prevent network traffic from reaching its destination. Our research shows that BGP announcements that are associated with disruptive updates tend to occur in groups of relatively high frequency, followed by periods …
Machine learning (ML) has progressed rapidly during the past decade and the major factor that drives such development is the unprecedented large-scale data. As data generation is a continuous process, this leads to ML model owners updating their models frequently with newly-collected data in an online learning scenario…
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…
Study examines tech stocks' reactions to Facebook data leak scandal.
Bayesian approach quantifies uncertainty in LLM evaluations.
Active learning holds promise of significantly reducing data annotation costs while maintaining reasonable model performance. However, it requires sending data to annotators for labeling. This presents a possible privacy leak when the training set includes sensitive user data. In this paper, we describe an approach for…
Machine learning has been widely applied to various applications, some of which involve training with privacy-sensitive data. A modest number of data breaches have been studied, including credit card information in natural language data and identities from face dataset. However, most of these studies focus on supervise…
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…
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…
A new property fixes look-ahead bias in backtesting and trading pipelines.
Graph embedding leaks sensitive graph properties and subgraphs.
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…
We use the database leak of Mt. Gox exchange to analyze the dynamics of the price of bitcoin from June 2011 to November 2013. This gives us a rare opportunity to study an emerging retail-focused, highly speculative and unregulated market with trader identifiers at a tick transaction level. Jumps are frequent events and…
LFD method improves text classification by making features clearer and less label-leaking.
For graphs generated from stochastic blockmodels, adjacency spectral embedding is asymptotically consistent. Further, adjacency spectral embedding composed with universally consistent classifiers is universally consistent to achieve the Bayes error. However when the graph contains private or sensitive information, trea…
This paper analyzes how training data can be leaked from gradients in neural networks and proposes a metric for measuring model security.
Study confirms USD/JPY rises at Gotobi days, suggesting trading strategy.
Data privacy is an important issue for "machine learning as a service" providers. We focus on the problem of membership inference attacks: given a data sample and black-box access to a model's API, determine whether the sample existed in the model's training data. Our contribution is an investigation of this problem in…
Proposes QNN to protect input privacy in neural networks.
We present an approach based on machine learning (ML) to distinguish eruption and precursory signals of Chimayó geyser (New Mexico, USA) under noisy environments. This geyser can be considered as a natural analog of intrusion into shallow water aquifers. By studying this geyser, we can understand upwell…
Foundation models leak sensitive data in synthetic tabular data generation, especially LLaMA 3.3 70B.