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.
Differentially private algorithms protect model explanations from leaking training data.
DP-SGD analysis shows many datapoints leak less privacy than previously thought.
New analysis shows SGD with noise doesn't leak more privacy with more iterations.
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…
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…
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…
This paper studies trade-offs in private prediction methods.
Develops DP-SCD for stochastic coordinate descent, making it differentially private.
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…
Federated learning leaks participant dataset quality even with secure aggregation.
DarkneTZ protects edge devices from DNN model leaks using TEE and model partitioning.
Proposes QNN to protect input privacy in neural networks.
Paper evaluates and improves private feature selection methods.
Proposes a privacy-preserving recommendation system using matrix factorization and differential privacy.
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…
Differential Privacy (DP) provides strong guarantees on the risk of compromising a user's data in statistical learning applications, though these strong protections make learning challenging and may be too stringent for some use cases. To address this, we propose element level differential privacy, which extends differ…
Latent Dirichlet Allocation (LDA) is a popular topic modeling technique for discovery of hidden semantic architecture of text datasets, and plays a fundamental role in many machine learning applications. However, like many other machine learning algorithms, the process of training a LDA model may leak the sensitive inf…
Synthetic data can amplify privacy in linear regression models.
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…
Privacy concerns have led to the development of privacy-preserving approaches for learning models from sensitive data. Yet, in practice, even models learned with privacy guarantees can inadvertently memorize unique training examples or leak sensitive features. To identify such privacy violations, existing model auditin…
New approach protects privacy of deleted records in machine learning.
Language models learn from training data and can leak private information.
New algorithms protect user-level privacy in learning tasks.
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…
Differential privacy is a strong notion for privacy that can be used to prove formal guarantees, in terms of a privacy budget, , about how much information is leaked by a mechanism. However, implementations of privacy-preserving machine learning often select large values of in order to get acceptable utility of …
The paper investigates how data imbalance affects fairness and accuracy in differentially private deep learning.
TVineSynth generates synthetic data to balance privacy and utility.
Foundation models leak sensitive data in synthetic tabular data generation, especially LLaMA 3.3 70B.
FEDMD-NFDP improves federated learning privacy without sacrificing performance.
Survey on privacy issues in deep learning and proposed solutions.
Paper reconstructs training data from a single gradient query.
Researchers found PP-GANs can hide sensitive data in sanitized images, undermining privacy checks.
Paper shows Cox model optimisation leaks patient data in distributed learning.
This research examines rare spurious correlations in neural networks and their impact on accuracy and privacy.
This paper improves deep learning models' accuracy with differential privacy using gradient encoding and denoising.
RENNs protect input privacy by rotating d-ary features.
Secure XGB for privacy-preserving machine learning in federated learning.
PRIME algorithm estimates mean while ensuring privacy and robustness.
Collaborative learning allows participants to jointly train a model without data sharing. To update the model parameters, the central server broadcasts model parameters to the clients, and the clients send updating directions such as gradients to the server. While data do not leave a client device, the communicated gra…
This paper analyzes FL privacy risks and defensive strategies.
Differential privacy for simple linear regression protects small datasets from individual data leaks.
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…
Paper introduces differential pairwise privacy for secure metric learning.
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…
HDP-VFL hybridizes DP for VFL, reducing privacy costs.
Strategic information is valuable either by remaining private (for instance if it is sensitive) or, on the other hand, by being used publicly to increase some utility. These two objectives are antagonistic and leaking this information might be more rewarding than concealing it. Unlike classical solutions that focus on …
Many mobile applications and virtual conversational agents now aim to recognize and adapt to emotions. To enable this, data are transmitted from users' devices and stored on central servers. Yet, these data contain sensitive information that could be used by mobile applications without user's consent or, maliciously, b…
Data privacy is an important concern in learning, when datasets contain sensitive information about individuals. This paper considers consensus-based distributed optimization under data privacy constraints. Consensus-based optimization consists of a set of computational nodes arranged in a graph, each having a local ob…