相关论文: Minimizing Risk Through Minimizing Model-Data Inte…

In 2022, AI image generators crossed a threshold, enabling much more efficient and dynamic production of photorealistic deepfake images than before. This enabled opportunities for creative and positive uses of these models. However, it also…

Counterfactual explanations have emerged as a prominent method in Explainable Artificial Intelligence (XAI), providing intuitive and actionable insights into Machine Learning model decisions. In contrast to other traditional feature…

Many smartphone apps transmit personally identifiable information (PII), often without the users knowledge. To address this issue, we present PrivacyProxy, a system that monitors outbound network traffic and generates app-specific…

Evaluating fairness can be challenging in practice because the sensitive attributes of data are often inaccessible due to privacy constraints. The go-to approach that the industry frequently adopts is using off-the-shelf proxy models to…

We present the first English corpus study on abusive language towards three conversational AI systems gathered "in the wild": an open-domain social bot, a rule-based chatbot, and a task-based system. To account for the complexity of the…

The use of ASCII art as a novel approach to masking sensitive information in cybercrime, focusing on its potential role in protecting personal data during the delivery process and beyond, is presented. By examining the unique properties of…

Deep learning models often learn to make predictions that rely on sensitive social attributes like gender and race, which poses significant fairness risks, especially in societal applications, e.g., hiring, banking, and criminal justice.…

The critical need for transparent and trustworthy machine learning in cybersecurity operations drives the development of this integrated Explainable AI (XAI) framework. Our methodology addresses three fundamental challenges in deploying AI…

The successful deployment of artificial intelligence (AI) in many domains from healthcare to hiring requires their responsible use, particularly in model explanations and privacy. Explainable artificial intelligence (XAI) provides more…

One of the biggest bottlenecks in a machine learning workflow is waiting for models to train. Depending on the available computing resources, it can take days to weeks to train a neural network on a large dataset with many classes such as…

Prevailing image representation methods, including explicit representations such as raster images and Gaussian primitives, as well as implicit representations such as latent images, either suffer from representation redundancy that leads to…

Anomaly detection in medical images refers to the identification of abnormal images with only normal images in the training set. Most existing methods solve this problem with a self-reconstruction framework, which tends to learn an identity…

Test-time task adaptation in few-shot learning aims to adapt a pre-trained task-agnostic model for capturing taskspecific knowledge of the test task, rely only on few-labeled support samples. Previous approaches generally focus on…

In this work we study the problem of measuring the fairness of a machine learning model under noisy information. Focusing on group fairness metrics, we investigate the particular but common situation when the evaluation requires controlling…

The detection of online cyberbullying has seen an increase in societal importance, popularity in research, and available open data. Nevertheless, while computational power and affordability of resources continue to increase, the access…

The development of generative artificial intelligence (AI) tools capable of producing wholly or partially synthetic child sexual abuse material (AI CSAM) presents profound challenges for child protection, law enforcement, and societal…

Financial cybercrime prevention is an increasing issue with many organisations and governments. As deep learning models have progressed to identify illicit activity on various financial and social networks, the explainability behind the…

Diffusion models (DMs) embark a new era of generative modeling and offer more opportunities for efficient generating high-quality and realistic data samples. However, their widespread use has also brought forth new challenges in model…

If generalist robots are to operate in truly unstructured environments, they need to be able to recognize and reason about novel objects and scenarios. Such objects and scenarios might not be present in the robot's own training data. We…

Machine learnt systems inherit biases against protected classes, historically disparaged groups, from training data. Usually, these biases are not explicit, they rely on subtle correlations discovered by training algorithms, and are…