相关论文: Machine learning attack on copy detection patterns…

Data reconstruction attacks on machine learning models pose a substantial threat to privacy, potentially leaking sensitive information. Although defending against such attacks using differential privacy (DP) provides theoretical guarantees,…

In statistical setting of the pattern recognition problem the number of examples required to approximate an unknown labelling function is linear in the VC dimension of the target learning class. In this work we consider the question whether…

The field of big code relies on mining large corpora of code to perform some learning task. A significant threat to this approach has been recently identified by Lopes et al. (2017) who found a large amount of near-duplicate code on GitHub.…

The powerful no-cloning principle of quantum mechanics can be leveraged to achieve interesting primitives, referred to as unclonable primitives, that are impossible to achieve classically. In the past few years, we have witnessed a surge of…

In this research, we analyzed the suitability of each of the current state-of-the-art machine learning models for various cyberattack detection from the past 5 years with a major emphasis on the most recent works for comparative study to…

We study the problem of detecting change points (CPs) that are characterized by a subset of dimensions in a multi-dimensional sequence. A method for detecting those CPs can be formulated as a two-stage method: one for selecting relevant…

Machine-learning architectures, such as Convolutional Neural Networks (CNNs) are vulnerable to adversarial attacks: inputs crafted carefully to force the system output to a wrong label. Since machine-learning is being deployed in…

The training and creation of deep learning model is usually costly, thus it can be regarded as an intellectual property (IP) of the model creator. However, malicious users who obtain high-performance models may illegally copy, redistribute,…

Label differential privacy (DP) is designed for learning problems involving private labels and public features. While various methods have been proposed for learning under label DP, the theoretical limits remain largely unexplored. In this…

Software clone detection identifies similar code snippets. It has been an active research topic that attracts extensive attention over the last two decades. In recent years, machine learning (ML) based detectors, especially deep…

Deep image classification models trained on vast amounts of web-scraped data are susceptible to data poisoning - a mechanism for backdooring models. A small number of poisoned samples seen during training can severely undermine a model's…

Model stealing attacks endanger the confidentiality of machine learning models offered as a service. Although these models are kept secret, a malicious party can query a model to label data samples and train their own substitute model,…

Split conformal prediction (CP) is arguably the most popular CP method for uncertainty quantification, enjoying both academic interest and widespread deployment. However, the original theoretical analysis of split CP makes the crucial…

Cyber security can be enhanced through application of machine learning by recasting network attack data into an image format, then applying supervised computer vision and other machine learning techniques to detect malicious specimens.…

Model-sharing offers significant business value by enabling firms with well-established Machine Learning (ML) models to monetize and share their models with others who lack the resources to develop ML models from scratch. However, concerns…

There are a great many clone detection tools proposed in the literature. In this paper, we investigate the state of clone detection tool evaluation. We begin by surveying the clone detection benchmarks, and performing a multi-faceted…

Large language models (LLMs) have demonstrated remarkable capabilities in various software engineering tasks, such as code generation and debugging, because of their ability to translate between programming languages and natural languages.…

Methods from machine learning are being applied to design Industrial Control Systems resilient to cyber-attacks. Such methods focus on two major areas: the detection of intrusions at the network-level using the information acquired through…

In this note, we consider the setting of uncloneable encryption satisfying uncloneable indistinguishability, a form of symmetric key encryption that prevents the cloning of ciphertexts in a very strong sense. Our goal is to minimize the…

In response to adversarial text attacks, attack detection models have been proposed and shown to successfully identify text modified by adversaries. Attack detection models can be leveraged to provide an additional check for NLP models and…