English
Related papers

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

200 papers

Concept Bottleneck Models (CBMs) ground image classification on human-understandable concepts to allow for interpretable model decisions. Crucially, the CBM design inherently allows for human interventions, in which expert users are given…

Machine Learning · Computer Science 2024-08-07 Nishad Singhi , Jae Myung Kim , Karsten Roth , Zeynep Akata

In-Context Learning (ICL) has become a standard technique for adapting Large Language Models (LLMs) to specialized tasks by supplying task-specific exemplars within the prompt. However, when these exemplars contain sensitive information,…

Cryptography and Security · Computer Science 2026-04-22 Jacob Choi , Shuying Cao , Xingjian Dong , Amin Banayeeanzade , Wang Bill Zhu , Robin Jia , Sai Praneeth Karimireddy

Quantitative theories of information flow give us an approach to relax the absolute confidentiality properties that are difficult to satisfy for many practical programs. The classical information-theoretic approaches for sequential…

Cryptography and Security · Computer Science 2013-06-13 Tri Minh Ngo , Marieke Huisman

Concept Bottleneck Models (CBMs) have emerged as a prominent paradigm for interpretable deep learning, learning by grounding predictions in human-understandable concepts. However, their practical deployment is hindered by the high cost of…

Machine Learning · Computer Science 2026-05-29 Ziye Chen , Hongbin Lin , Jie Li , Lijie Hu

Semantic leakage is a phenomenon recently introduced by Gonen et al. (2024). It refers to a situation in which associations learnt from the training data emerge in language model generations in an unexpected and sometimes undesired way.…

Computation and Language · Computer Science 2025-01-14 Veronika Smilga

A new measure of information leakage for quantum encoding of classical data is defined. An adversary can access a single copy of the state of a quantum system that encodes some classical data and is interested in correctly guessing a…

Quantum Physics · Physics 2024-02-20 Farhad Farokhi

We introduce a privacy measure called pointwise maximal leakage, generalizing the pre-existing notion of maximal leakage, which quantifies the amount of information leaking about a secret $X$ by disclosing a single outcome of a (randomized)…

Information Theory · Computer Science 2023-08-16 Sara Saeidian , Giulia Cervia , Tobias J. Oechtering , Mikael Skoglund

With the growing popularity of general-purpose Large Language Models (LLMs), comes a need for more global explanations of model behaviors. Concept-based explanations arise as a promising avenue for explaining high-level patterns learned by…

Artificial Intelligence · Computer Science 2024-10-07 Meng Li , Haoran Jin , Ruixuan Huang , Zhihao Xu , Defu Lian , Zijia Lin , Di Zhang , Xiting Wang

Concept Bottleneck Models (CBMs) try to make the decision-making process transparent by exploring an intermediate concept space between the input image and the output prediction. Existing CBMs just learn coarse-grained relations between the…

Computer Vision and Pattern Recognition · Computer Science 2025-05-13 Yan Xie , Zequn Zeng , Hao Zhang , Yucheng Ding , Yi Wang , Zhengjue Wang , Bo Chen , Hongwei Liu

The concept bottleneck model (CBM), as a technique improving interpretability via linking predictions to human-understandable concepts, makes high-risk and life-critical medical image classification credible. Typically, existing CBM methods…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Chunjiang Wang , Kun Zhang , Yandong Liu , Zhiyang He , Xiaodong Tao , S. Kevin Zhou

Embeddings are functions that map raw input data to low-dimensional vector representations, while preserving important semantic information about the inputs. Pre-training embeddings on a large amount of unlabeled data and fine-tuning them…

Machine Learning · Computer Science 2020-08-21 Congzheng Song , Ananth Raghunathan

Deep learning models, particularly Long Short-Term Memory (LSTM) networks, are widely used in time series forecasting due to their ability to capture complex temporal dependencies. However, evaluation integrity is often compromised by data…

Machine Learning · Computer Science 2025-12-09 Salma Albelali , Moataz Ahmed

Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy. Concept bottleneck models promote trustworthiness by conditioning classification tasks on an…

Concept Bottleneck Models (CBMs) have garnered increasing attention due to their ability to provide concept-based explanations for black-box deep learning models while achieving high final prediction accuracy using human-like concepts.…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Lijie Hu , Tianhao Huang , Huanyi Xie , Xilin Gong , Chenyang Ren , Zhengyu Hu , Lu Yu , Ping Ma , Di Wang

In recent years, the black-box nature of deep learning models has limited their application in high-stakes domains such as medical diagnosis and finance, where interpretability is essential. To address this, we propose a novel approach…

Computation and Language · Computer Science 2026-05-26 Yike Sun , Mingkun Xu , Mu You , Zhongzhi He , Henghua Shen , Zehan Tan , Derek F. Wong , Tao Fang

Machine-learning models contain information about the data they were trained on. This information leaks either through the model itself or through predictions made by the model. Consequently, when the training data contains sensitive…

Machine Learning · Computer Science 2021-08-25 Awni Hannun , Chuan Guo , Laurens van der Maaten

Amid the expanding use of pre-training data, the phenomenon of benchmark dataset leakage has become increasingly prominent, exacerbated by opaque training processes and the often undisclosed inclusion of supervised data in contemporary…

Computation and Language · Computer Science 2024-04-30 Ruijie Xu , Zengzhi Wang , Run-Ze Fan , Pengfei Liu

Concept Bottleneck Models (CBMs) are a prominent framework for interpretable AI that map learned visual features to a set of meaningful concepts for task-specific downstream predictions. Their sequential structure enhances transparency by…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Mohamed Harmanani , Bining Long , Zhuoxin Guo , Paul F. R. Wilson , Amirhossein Sabour , Minh Nguyen Nhat To , Gabor Fichtinger , Purang Abolmaesumi , Parvin Mousavi

This paper introduces a novel problem, distributional information embedding, motivated by the practical demands of multi-bit watermarking for large language models (LLMs). Unlike traditional information embedding, which embeds information…

Cryptography and Security · Computer Science 2025-07-03 Haiyun He , Yepeng Liu , Ziqiao Wang , Yongyi Mao , Yuheng Bu

Large language models (LLMs) have advanced natural language processing (NLP) skills such as through next-token prediction and self-attention, but their ability to integrate broad context also makes them prone to incorporating irrelevant…