Related papers: An Incremental Learner for Language-Based Anomaly …

Adversarial attacks are a serious threat to the reliable deployment of machine learning models in safety-critical applications. They can misguide current models to predict incorrectly by slightly modifying the inputs. Recently, substantial…

Within research institutions like CERN (European Organization for Nuclear Research) there are often disparate databases (different in format, type and structure) that users need to access in a domain-specific manner. Users may want to…

Variational autoencoders learn unsupervised data representations, but these models frequently converge to minima that fail to preserve meaningful semantic information. For example, variational autoencoders with autoregressive decoders often…

Distributed machine learning algorithms play a significant role in processing massive data sets over large networks. However, the increasing reliance on machine learning on information and communication technologies (ICTs) makes it…

Extended reality (XR) applications increasingly integrate Large Language Models (LLMs) to enhance user experience, scene understanding, and even generate executable XR content, and are often called "AI glasses". Despite these potential…

The paper studies the rewriting mechanisms for intensional documents in the Active XML framework, abstracted in the form of active context-free games. The safe rewriting problem studied in this paper is to decide whether the first player,…

We propose a new language feature for ML-family languages, the ability to selectively unbox certain data constructors, so that their runtime representation gets compiled away to just the identity on their argument. Unboxing must be…

Machine learning algorithms are increasingly being applied in security-related tasks such as spam and malware detection, although their security properties against deliberate attacks have not yet been widely understood. Intelligent and…

XML is based on two essential aspects: the modelization of data in a tree like structure and the separation between the information itself and the way it is displayed. XML structures are easily serializable. The separation between an…

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels…

AI coding assistants are widely used for tasks like code generation. These tools now require large and complex contexts, automatically sourced from various origins$\unicode{x2014}$across files, projects, and…

Language Models (LMs) are prone to ''memorizing'' training data, including substantial sensitive user information. To mitigate privacy risks and safeguard the right to be forgotten, machine unlearning has emerged as a promising approach for…

Traditional approaches to safety event analysis in autonomous systems have relied on complex machine learning models and extensive datasets for high accuracy and reliability. However, the advent of Multimodal Large Language Models (MLLMs)…

Web applications suffer from cross-site scripting (XSS) attacks that resulting from incomplete or incorrect input sanitization. Learning the structure of attack vectors could enrich the variety of manifestations in generated XSS attacks. In…

Multimodal large language models (MLLMs) have shown impressive reasoning abilities. However, they are also more vulnerable to jailbreak attacks than their LLM predecessors. Although still capable of detecting the unsafe responses, we…

Automatic vision inspection holds significant importance in industry inspection. While multimodal large language models (MLLMs) exhibit strong language understanding capabilities and hold promise for this task, their performance remains…

An anomaly detection method based on deep autoencoders is proposed to address anomalies that often occur in enterprise-level ETL data streams. The study first analyzes multiple types of anomalies in ETL processes, including delays, missing…

Supervised-learning-based vulnerability detectors often fall short due to limited labelled training data. In contrast, Large Language Models (LLMs) like GPT-4 are trained on vast unlabelled code corpora, yet perform only marginally better…

With the increasing frequency and sophistication of Distributed Denial of Service (DDoS) attacks, it has become critical to develop more efficient and interpretable detection methods. Traditional detection systems often struggle with…

XSLT is an increasingly popular language for processing XML data. It is widely supported by application platform software. However, little optimization effort has been made inside the current XSLT processing engines. Evaluating a very…