Related papers: Resilience to the Flowing Unknown: an Open Set Rec…

Before deployment in the real-world deep neural networks require thorough evaluation of how they handle both knowns, inputs represented in the training data, and unknowns (anomalies). This is especially important for scene understanding…

The wide spread usage of automated data-driven decision support systems has raised a lot of concerns regarding accountability and fairness of the employed models in the absence of human supervision. Existing fairness-aware approaches tackle…

The amount of data for processing and categorization grows at an ever increasing rate. At the same time the demand for collaboration and transparency in organizations, government and businesses, drives the release of data from internal…

Artificial intelligence (AI) based device identification improves the security of the internet of things (IoT), and accelerates the authentication process. However, existing approaches rely on the assumption that we can learn all the…

Processing data streams arriving at high speed requires the development of models that can provide fast and accurate predictions. Although deep neural networks are the state-of-the-art for many machine learning tasks, their performance in…

The paper explores the challenges of regression analysis in evolving data streams, an area that remains relatively underexplored compared to classification. We propose a standardized evaluation process for regression and prediction interval…

Open set recognition problems exist in many domains. For example in security, new malware classes emerge regularly; therefore malware classification systems need to identify instances from unknown classes in addition to discriminating…

Existing open set recognition (OSR) methods are typically designed for static scenarios, where models aim to classify known classes and identify unknown ones within fixed scopes. This deviates from the expectation that the model should…

Rising concern for the societal implications of artificial intelligence systems has inspired demands for greater transparency and accountability. However the datasets which empower machine learning are often used, shared and re-used with…

Data-driven science is an emerging paradigm where scientific discoveries depend on the execution of computational AI models against rich, discipline-specific datasets. With modern machine learning frameworks, anyone can develop and execute…

Multi-view learning methods leverage multiple data sources to enhance perception by mining correlations across views, typically relying on predefined categories. However, deploying these models in real-world scenarios presents two primary…

Cloud networks increasingly rely on machine learning based Network Intrusion Detection Systems to defend against evolving cyber threats. However, real-world deployments are challenged by limited labeled data, non-stationary traffic, and…

The concept of evolving intelligent system (EIS) provides an effective avenue for data stream mining because it is capable of coping with two prominent issues: online learning and rapidly changing environments. We note at least three…

Incident monitoring can drive safety improvements in high-reliability industries and population-scale technologies, but remains underdeveloped in AI governance. Public databases catalog thousands of AI incidents, but simple incident counts…

The primary assumption of conventional supervised learning or classification is that the test samples are drawn from the same distribution as the training samples, which is called closed set learning or classification. In many practical…

Data collection at a massive scale is becoming ubiquitous in a wide variety of settings, from vast offline databases to streaming real-time information. Learning algorithms deployed in such contexts must rely on single-pass inference, where…

Pioneered by the foundational information theory by Claude Shannon and the visionary framework of machine intelligence by Alan Turing, the convergent evolution of information and communication technologies (IT/CT) has created an unbroken…

Ensuring the reliability and safety of machine learning models in open-world deployment is a central challenge in AI safety. This thesis develops both algorithmic and theoretical foundations to address key reliability issues arising from…

Handling entirely unknown data is a challenge for any deployed classifier. Classification models are typically trained on a static pre-defined dataset and are kept in the dark for the open unassigned feature space. As a result, they…

Current deep learning methods are regarded as favorable if they empirically perform well on dedicated test sets. This mentality is seamlessly reflected in the resurfacing area of continual learning, where consecutively arriving data is…