Suggested research questions
(These are flexible and can be specified after your requirements):

Q1: How can generative AI models be optimized to generate accurate and context-specific responses for questionnaires?

Q2: How does automating questionnaire responses using AI impact:

- organizational efficiency and

- what risk are associated with such an automation?

Read more here: https://career.centiro.com/jobs/5072071-leveraging-generative-ai-for-automating-questionnaire-responses/d9d5672a-f82d-4365-a78e-33bdb947072f

Carriers’ transportation networks can be interpreted as directed graphs. Edges are defined as routes containing information about distance, transport mode, and shipments’ weight. Nodes are defined as hubs/warehouses and source/destination points. A transport chain in a network is equivalent to a shipment travelling from a source- to a destination node and can be viewed as a Markov chain process. Furthermore, the shipments’ tracking events can be used to model and assert the intermediary nodes between the source and destination nodes.

Areas of interest to explore:

- Learn or find existing policies in a transportation network determining the transport chains.

- Analysis of correlation between lead time, emission and distance.

- Applying machine learning for predicting future behavior.

- Simulate values for performance metrics using stochastic sampling from learned distributions with injecting, removing, or modifying nodes in the network and analyzing its impacts.

Read more here: https://career.centiro.com/jobs/5072109-learning-policies-in-transportation-networks-and-predicting-performance-metrics/851fd239-33a5-4042-adfd-0574dd88093f

Introduction

As machine learning models become integral to various industries, from healthcare and finance to social media and autonomous systems, the importance of data privacy and security has never been more critical. One of the most pressing concerns in this domain is the risk posed by model inversion attacks [1]. These attacks represent a significant threat to the privacy of individuals whose data may have been used in training machine learning models. By leveraging the outputs or internal states of a trained model, adversaries aim to reverse-engineer and reconstruct specific data points, revealing sensitive information about individuals or class representatives.

The danger of model inversion attacks lies in their ability to recreate underlying training data. For instance, an attacker may infer private attributes such as medical conditions, financial transactions, or personal behaviours based solely on the model’s predictions or intermediate outputs. This risk is particularly acute for models deployed in privacy-sensitive domains, where exposure of private data can have severe ethical, legal, and regulatory consequences.

Read more here: https://careers.ai.se/jobs/5066843-master-thesis-pulling-sensitive-data-from-trained-models

Introduction

Training deep-learning models require large amounts of data. When this data is sensitive, e.g., containing personal information, it is important to ensure that no information can be extracted from the trained models. Lately, adversarial attempts at extracting training data have grown in interest. Two prominent attacks are membership inference attacks, attempting to guess if a given data point was present in the training data, and reconstruction attacks, also called model-inversion attacks, which attempt to recreate training data by interacting with the trained model.

Although such attacks are relevant for any data modality, perhaps the most pressing issue pertains to text-data where the issue of copy-right has recently been in the media attention due to the lawsuit against Open-AI [8]. In light of this, there is a pressing need for content creators to confidently test whether or not their outputs have been included and leveraged in the training of commercial models. Membership inference attacks offer a promising venue for such an assessment.

Read more here: https://careers.ai.se/jobs/5076281-master-thesis-semantically-aware-attacks-on-text-based-modes

Introduction

In recent years, the application of machine learning models to analyze time series data has seen rapid growth across numerous industries, including finance, healthcare, energy, and the Internet of Things (IoT) [5]. However, as the use of these models becomes increasingly widespread, concerns regarding the privacy and security of the underlying data have intensified.

One particular privacy threat that has gained attention is the risk of membership inference attacks (MIAs) [2]. These attacks allow adversaries to determine whether a specific data point was part of a machine learning model’s training set. Such a capability can have serious consequences, especially when dealing with sensitive information such as financial transactions, medical histories, or proprietary business data. If adversaries can exploit these vulnerabilities, they may expose private information about individuals or gain insights into confidential datasets, thereby posing significant legal and ethical
challenges.

While much research has been conducted on membership inference attacks in domains like image classification and natural language processing, the vulnerability of time series-based models to these attacks have only been considered in few works [4, 3]. Time series data has unique properties—such as temporal dependencies and correlations—that could potentially influence the efficacy and nature of MIAs. Given the increasing reliance on machine learning models to process time series data in critical applications, it is essential to investigate the extent to which such models are susceptible to MIAs.

Read more here: https://careers.ai.se/jobs/5076413-master-thesis-privacy-risks-in-time-series-models

Introduction

Machine learning models are now indispensable across numerous sectors, from healthcare to finance, where they routinely handle sensitive personal data. While these models offer significant benefits, they also raise critical privacy concerns. One of the most pressing issues is the potential for adversaries to deduce whether specific data points were part of a model’s training set, a vulnerability exploited through Membership Inference Attacks (MIAs). These attacks pose serious privacy risks, allowing malicious actors to infer sensitive information about individuals.

Much of the existing research focuses on MIAs that target exact data points in the training set [4, 8]. However, an important and often overlooked threat lies in range membership inference attacks [7, 6]. These attacks exploit the similarities between new data and training data, allowing adversaries to infer information about data points that are close—but not identical—to those used in training. This gap in the literature represents a significant privacy risk, as these near-identical data points can contain similarly sensitive information.

This thesis will investigate range membership inference attacks and evaluate their impact on the privacy of machine learning models. By extending the scope of traditional MIAs, the goal is to establish a broader understanding of actual risks when adversaries are not interested in inferring exact data points but only approximations.

Read more here: https://careers.ai.se/jobs/5076487-master-thesis-similarity-based-inference-attacks