Related papers: Black Boxes, White Noise: Similarity Detection for…

Binary function similarity, which often relies on learning-based algorithms to identify what functions in a pool are most similar to a given query function, is a sought-after topic in different communities, including machine learning,…

Deep neural networks (DNNs) are widely used in various application domains such as image processing, speech recognition, and natural language processing. However, testing DNN models may be challenging due to the complexity and size of their…

The increasing reliance on large language models (LLMs) in academic writing has led to a rise in plagiarism. Existing AI-generated text classifiers have limited accuracy and often produce false positives. We propose a novel approach using…

Deep learning algorithms are growing in popularity in the field of exoplanetary science due to their ability to model highly non-linear relations and solve interesting problems in a data-driven manner. Several works have attempted to…

This paper considers the problem of helping humans exercise scalable oversight over deep neural networks (DNNs). Adversarial examples can be useful by helping to reveal weaknesses in DNNs, but they can be difficult to interpret or draw…

Having similar code fragments, also called clones, in software systems can lead to unnecessary comprehension, review and change efforts. Syntactically similar clones can often be encountered in practice. The same is not clear for only…

Finding the same or similar code snippets in source code is one of fundamental activities in software maintenance. Text-based pattern matching tools such as grep is frequently used for such purpose, but making proper queries for the…

Measuring plagiarism in programming assignments is an essential task to the educational procedure. This paper discusses the methods of plagiarism and its detection in introductory programming course assignments written in C++. A small…

This paper makes a substantial step towards cloning the functionality of black-box models by introducing a Machine learning (ML) architecture named Deep Neural Trees (DNTs). This new architecture can learn to separate different tasks of the…

The black box nature of deep learning models complicate their usage in critical applications such as remote sensing. Conformal prediction is a method to ensure trust in such scenarios. Subject to data exchangeability, conformal prediction…

Vulnerability detection is crucial to protect software security. Nowadays, deep learning (DL) is the most promising technique to automate this detection task, leveraging its superior ability to extract patterns and representations within…

Deep Neural Networks (DNN) are computationally intensive to train. It consists of a large number of multidimensional dot products between many weights and input vectors. However, there can be significant similarity among input vectors. If…

Collaborative inference of object classification Deep neural Networks (DNNs) where resource-constrained end-devices offload partially processed data to remote edge servers to complete end-to-end processing, is becoming a key enabler of…

How do we know if two systems - biological or artificial - process information in a similar way? Similarity measures such as linear regression, Centered Kernel Alignment (CKA), Normalized Bures Similarity (NBS), and angular Procrustes…

Approximate matching (AM) is a concept in digital forensics to determine the similarity between digital artifacts. An important use case of AM is the reliable and efficient detection of case-relevant data structures on a blacklist, if only…

The black-box nature of deep neural networks (DNNs) makes it impossible to understand why a particular output is produced, creating demand for "Explainable AI". In this paper, we show that statistical fault localization (SFL) techniques…

A code clone is a pair of code fragments, within or between software systems that are similar. Since code clones often negatively impact the maintainability of a software system, several code clone detection techniques and tools have been…

The gap between low-level visual signals and high-level semantics has been progressively bridged by continuous development of deep neural network (DNN). With recent progress of DNN, almost all image classification tasks have achieved new…

We employ a toolset -- dubbed Dr. Frankenstein -- to analyse the similarity of representations in deep neural networks. With this toolset, we aim to match the activations on given layers of two trained neural networks by joining them with a…

Deep neural network (DNN) models have achieved phenomenal success for applications in many domains, ranging from academic research in science and engineering to industry and business. The modeling power of DNN is believed to have come from…