English
Related papers

Related papers: Forensicability of Deep Neural Network Inference P…

200 papers

Identifiability is a desirable property of a statistical model: it implies that the true model parameters may be estimated to any desired precision, given sufficient computational resources and data. We study identifiability in the context…

Machine Learning · Statistics 2020-07-09 Geoffrey Roeder , Luke Metz , Diederik P. Kingma

Deep Learning models are vulnerable to adversarial examples, i.e.\ images obtained via deliberate imperceptible perturbations, such that the model misclassifies them with high confidence. However, class confidence by itself is an incomplete…

Machine Learning · Statistics 2017-11-23 Ambrish Rawat , Martin Wistuba , Maria-Irina Nicolae

The deployment of AI systems in safety-critical domains, such as industrial defect inspection, autonomous driving, and medical diagnosis, is severely hampered by their lack of reliability. A single undetected erroneous prediction can lead…

Computer Vision and Pattern Recognition · Computer Science 2026-04-22 Hang-Cheng Dong , Yuhao Jiang , Yibo Jiao , Lu Zou , Kai Zheng , Bingguo Liu , Dong Ye , Guodong Liu

The behavior of LLMs does not depend solely on the model itself. Components of the inference system, such as the inference engine, attention backend, and hardware platform, subtly influence how inputs are processed. These components differ…

Cryptography and Security · Computer Science 2026-05-29 Anna Wimbauer , Jonas Möller , Erik Imgrund , Konrad Rieck

When neural networks are employed for high-stakes decision-making, it is desirable that they provide explanations for their prediction in order for us to understand the features that have contributed to the decision. At the same time, it is…

Machine Learning · Computer Science 2022-05-10 Penny Chong , Ngai-Man Cheung , Yuval Elovici , Alexander Binder

There have been extensive studies on solving differential equations using physics-informed neural networks. While this method has proven advantageous in many cases, a major criticism lies in its lack of analytical error bounds. Therefore,…

Neural and Evolutionary Computing · Computer Science 2022-07-05 Shuheng Liu , Xiyue Huang , Pavlos Protopapas

In variational inference, the benefits of Bayesian models rely on accurately capturing the true posterior distribution. We propose using neural samplers that specify implicit distributions, which are well-suited for approximating complex…

Machine Learning · Computer Science 2023-11-10 Anshuk Uppal , Kristoffer Stensbo-Smidt , Wouter Boomsma , Jes Frellsen

We introduce a causal modeling framework that captures the input-output behavior of predictive models (e.g., machine learning models). The framework enables us to identify features that directly cause the predictions, which has broad…

Machine Learning · Computer Science 2025-05-20 Yizuo Chen , Amit Bhatia

This paper presents a machine learning framework for Bayesian systems identification from noisy, sparse and irregular observations of nonlinear dynamical systems. The proposed method takes advantage of recent developments in differentiable…

Machine Learning · Computer Science 2020-04-21 Yibo Yang , Mohamed Aziz Bhouri , Paris Perdikaris

Many forensic genetics problems can be handled using structured systems of discrete variables, for which Bayesian networks offer an appealing practical modeling framework, and allow inferences to be computed by probability propagation…

Applications · Statistics 2009-08-21 Peter J. Green , Julia Mortera

Recently, there has been considerable progress on designing algorithms with provable guarantees -- typically using linear algebraic methods -- for parameter learning in latent variable models. But designing provable algorithms for inference…

Machine Learning · Computer Science 2016-05-30 Sanjeev Arora , Rong Ge , Frederic Koehler , Tengyu Ma , Ankur Moitra

Deep learning models have been developed for a variety of tasks and are deployed every day to work in real conditions. Some of these tasks are critical and models need to be trusted and safe, e.g. military communications or cancer…

Machine Learning · Computer Science 2023-11-13 Hélion du Mas des Bourboux

Deep neural networks are widely used for classification. These deep models often suffer from a lack of interpretability -- they are particularly difficult to understand because of their non-linear nature. As a result, neural networks are…

Artificial Intelligence · Computer Science 2017-11-22 Oscar Li , Hao Liu , Chaofan Chen , Cynthia Rudin

Deep learning adoption in the financial services industry has been limited due to a lack of model interpretability. However, several techniques have been proposed to explain predictions made by a neural network. We provide an initial…

Machine Learning · Computer Science 2018-12-04 Ceena Modarres , Mark Ibrahim , Melissa Louie , John Paisley

In recent years, there has been a significant surge in malware attacks, necessitating more advanced preventive measures and remedial strategies. While several successful AI-based malware classification approaches exist categorized into…

Cryptography and Security · Computer Science 2024-04-22 Quincy Card , Daniel Simpson , Kshitiz Aryal , Maanak Gupta , Sheikh Rabiul Islam

Neural networks are known to be effective function approximators. Recently, deep neural networks have proven to be very effective in pattern recognition, classification tasks and human-level control to model highly nonlinear realworld…

Neural and Evolutionary Computing · Computer Science 2016-10-06 Olalekan Ogunmolu , Xuejun Gu , Steve Jiang , Nicholas Gans

Neural networks are among the most accurate supervised learning methods in use today, but their opacity makes them difficult to trust in critical applications, especially when conditions in training differ from those in test. Recent work on…

Machine Learning · Computer Science 2017-11-15 Andrew Slavin Ross , Michael C. Hughes , Finale Doshi-Velez

Researchers develop models to explain the unknowns. These models typically involve parameters that capture tangible quantities, the estimation of which is desired. Parameter identifiability investigates the recoverability of the unknown…

Optimization and Control · Mathematics 2024-07-01 Anuththara Sarathchandra , Azadeh Aghaeeyan , Pouria Ramazi

Deep neural networks are often ignorant about what they do not know and overconfident when they make uninformed predictions. Some recent approaches quantify classification uncertainty directly by training the model to output high…

Machine Learning · Computer Science 2020-06-09 Murat Sensoy , Lance Kaplan , Federico Cerutti , Maryam Saleki

Machine Learning approaches are good in solving problems that have less information. In most cases, the software domain problems characterize as a process of learning that depend on the various circumstances and changes accordingly. A…

Software Engineering · Computer Science 2015-06-26 Saiqa Aleem , Luiz Fernando Capretz , Faheem Ahmed