Related papers: Efficient Data-Free Model Stealing with Label Dive…

Machine learning (ML) is increasingly being deployed in critical systems. The data dependence of ML makes securing data used to train and test ML-enabled systems of utmost importance. While the field of cybersecurity has well-established…

Machine learning (ML) is an important part of modern data science applications. Data scientists today have to manage the end-to-end ML life cycle that includes both model training and model serving, the latter of which is essential, as it…

Large language models (LLMs) demonstrate remarkable capabilities across various tasks. However, their deployment introduces significant risks related to intellectual property. In this context, we focus on model stealing attacks, where…

As Artificial Intelligence (AI) technologies continue to gain traction in the modern-day world, they ultimately pose an immediate threat to current cybersecurity systems via exploitative methods. Prompt engineering is a relatively new field…

Improving performance in multiple domains is a challenging task, and often requires significant amounts of data to train and test models. Active learning techniques provide a promising solution by enabling models to select the most…

Machine learning models are increasingly used in fields that require high reliability such as cybersecurity. However, these models remain vulnerable to various attacks, among which the adversarial label-flipping attack poses significant…

Federated learning (FL) attempts to train a global model by aggregating local models from distributed devices under the coordination of a central server. However, the existence of a large number of heterogeneous devices makes FL vulnerable…

As a long-term threat to the privacy of training data, membership inference attacks (MIAs) emerge ubiquitously in machine learning models. Existing works evidence strong connection between the distinguishability of the training and testing…

Federated learning (FL) enables privacy-preserving model training by keeping data decentralized. However, it remains vulnerable to label-flipping attacks, where malicious clients manipulate labels to poison the global model. Despite their…

Split Learning (SL) is a collaborative learning approach that improves privacy by keeping data on the client-side while sharing only the intermediate output with a server. However, the distributed nature of SL introduces new security…

Hyperparameters are critical in machine learning, as different hyperparameters often result in models with significantly different performance. Hyperparameters may be deemed confidential because of their commercial value and the…

We analyze Defragmentation-as-a-Service (DaaS) in elastic optical networks and show that the positive effect of defragmentation depends on the rate at which it is performed, load (or, call arrival rates) and the available resources.

In security-sensitive applications, the success of machine learning depends on a thorough vetting of their resistance to adversarial data. In one pertinent, well-motivated attack scenario, an adversary may attempt to evade a deployed system…

The uses of Machine Learning (ML) in detection of network attacks have been effective when designed and evaluated in a single organisation. However, it has been very challenging to design an ML-based detection system by utilising…

MLaaS (Machine Learning as a Service) has become popular in the cloud computing domain, allowing users to leverage cloud resources for running private inference of ML models on their data. However, ensuring user input privacy and secure…

The emerging wide area monitoring systems (WAMS) have brought significant improvements in electric grids' situational awareness. However, the newly introduced system can potentially increase the risk of cyber-attacks, which may be disguised…

Quantum machine learning (QML) is a category of algorithms that employ variational quantum circuits (VQCs) to tackle machine learning tasks. Recent discoveries have shown that QML models can effectively generalize from limited training data…

The usefulness and value of Multi-step Machine Learning (ML), where a task is organized into connected sub-tasks with known intermediate inference goals, as opposed to a single large model learned end-to-end without intermediate sub-tasks,…

Reinforcement Learning from Verifiable Rewards (RLVR) has significantly improved the reasoning capabilities of large language models (LLMs), particularly in multi-turn agentic settings involving environment interaction like tool use.…

Serverless computing is a widely adopted cloud execution model composed of Function-as-a-Service (FaaS) and Backend-as-a-Service (BaaS) offerings. The increased level of abstraction makes vendor lock-in inherent to serverless computing,…