English
Related papers

Related papers: Measuring Leakage in Concept-Based Methods: An Inf…

200 papers

Leakage errors are unwanted transfer of population outside of a defined computational subspace and they occur in almost every platform for quantum computing. While prevalent, leakage is often overlooked when measuring and reporting the…

Quantum Physics · Physics 2025-10-20 Yi-Hsiang Chen , Charles H. Baldwin

Interpretability is a crucial factor in building reliable models for various medical applications. Concept Bottleneck Models (CBMs) enable interpretable image classification by utilizing human-understandable concepts as intermediate…

Computer Vision and Pattern Recognition · Computer Science 2023-08-24 Injae Kim , Jongha Kim , Joonmyung Choi , Hyunwoo J. Kim

Concept Bottleneck Models (CBMs) have become a popular approach to enable interpretability in neural networks by constraining classifier inputs to a set of human-understandable concepts. While effective, current models embed concepts in…

Machine Learning · Computer Science 2026-05-13 Daniel Uyterlinde , Swasti Shreya Mishra , Pascal Mettes

We introduce Concept Bottleneck Large Language Models (CB-LLMs), a novel framework for building inherently interpretable Large Language Models (LLMs). In contrast to traditional black-box LLMs that rely on limited post-hoc interpretations,…

Computation and Language · Computer Science 2025-09-09 Chung-En Sun , Tuomas Oikarinen , Berk Ustun , Tsui-Wei Weng

Leakages are a major risk in water distribution networks as they cause water loss and increase contamination risks. Leakage detection is a difficult task due to the complex dynamics of water distribution networks. In particular, small…

Machine Learning · Computer Science 2024-01-04 Valerie Vaquet , Fabian Hinder , Barbara Hammer

The increasing use of neural networks in various applications has lead to increasing apprehensions, underscoring the necessity to understand their operations beyond mere final predictions. As a solution to enhance model transparency,…

Machine Learning · Computer Science 2023-11-21 Ivaxi Sheth , Samira Ebrahimi Kahou

Side-channel attacks that leak sensitive information through a computing device's interaction with its physical environment have proven to be a severe threat to devices' security, particularly when adversaries have unfettered physical…

Cryptography and Security · Computer Science 2021-06-15 Ileana Buhan , Lejla Batina , Yuval Yarom , Patrick Schaumont

Data leakage is the inadvertent transfer of information between training and evaluation datasets that poses a subtle, yet critical, risk to the reliability of machine learning (ML) models in safety-critical systems such as automotive…

Cryptography and Security · Computer Science 2026-04-09 Md Abu Ahammed Babu , Sushant Kumar Pandey , Darko Durisic , Andras Balint , Miroslaw Staron

While deep learning models often lack interpretability, concept bottleneck models (CBMs) provide inherent explanations via their concept representations. Moreover, they allow users to perform interventional interactions on these concepts by…

Machine Learning · Computer Science 2024-06-05 David Steinmann , Wolfgang Stammer , Felix Friedrich , Kristian Kersting

Deep Neural Networks (DNNs) are often considered black boxes due to their opaque decision-making processes. To reduce their opacity Concept Models (CMs), such as Concept Bottleneck Models (CBMs), were introduced to predict human-defined…

Human-Computer Interaction · Computer Science 2025-12-02 Jack Furby , Dan Cunnington , Dave Braines , Alun Preece

Concept-based eXplainable AI (C-XAI) is a rapidly growing research field that enhances AI model interpretability by leveraging intermediate, human-understandable concepts. This approach not only enhances model transparency but also enables…

Machine Learning · Computer Science 2025-04-08 Francesco De Santis , Gabriele Ciravegna , Philippe Bich , Danilo Giordano , Tania Cerquitelli

Concept Bottleneck Models (CBMs) have emerged as a cornerstone approach for interpretable machine learning, providing human-understandable intermediate representations through explicit concept activations. However, this interpretability…

Machine Learning · Computer Science 2026-05-26 Aditya Sridhar

A program is non-interferent if it leaks no secret information to an observable output. However, non-interference is too strict in many practical cases and quantitative information flow (QIF) has been proposed and studied in depth.…

Cryptography and Security · Computer Science 2019-10-23 Bao Trung Chu , Kenji Hashimoto , Hiroyuki Seki

The opaque nature of Large Language Models (LLMs) has led to significant research efforts aimed at enhancing their interpretability, primarily through post-hoc methods. More recent in-hoc approaches, such as Concept Bottleneck Models…

Machine Learning · Computer Science 2025-02-20 Or Raphael Bidusa , Shaul Markovitch

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…

Information Theory · Computer Science 2019-10-21 Hsiang Hsu , Shahab Asoodeh , Flavio du Pin Calmon

The increasing complexity of large language models (LLMs) raises concerns about their ability to "cheat" on standard Question Answering (QA) benchmarks by memorizing task-specific data. This undermines the validity of benchmark evaluations,…

Computation and Language · Computer Science 2025-09-16 Yixiong Fang , Tianran Sun , Yuling Shi , Min Wang , Xiaodong Gu

Recent work~\cite{Liu2016} has shown that dependencies between items in a dataset can lead to privacy leaks. We extend this concept to privacy-preserving transformations, considering a broader set of dependencies captured by correlation…

Cryptography and Security · Computer Science 2025-06-17 Kenneth Odoh

Large Language Models (LLMs) are trained on massive web-crawled corpora. This poses risks of leakage, including personal information, copyrighted texts, and benchmark datasets. Such leakage leads to undermining human trust in AI due to…

Computation and Language · Computer Science 2024-03-26 Masahiro Kaneko , Timothy Baldwin

The Information Bottleneck method is a learning technique that seeks a right balance between accuracy and generalization capability through a suitable tradeoff between compression complexity, measured by minimum description length, and…

Information Theory · Computer Science 2020-11-04 Mohammad Mahdi Mahvari , Mari Kobayashi , Abdellatif Zaidi

Machine learning (ML) approaches to data analysis are now widely adopted in many fields including epidemiology and medicine. To apply these approaches, confounds must first be removed as is commonly done by featurewise removal of their…

‹ Prev 1 4 5 6 7 8 10 Next ›