相关论文: Maintaining User Trust Through Multistage Uncertai…

This paper proposes a paradigm of uncertainty injection for training deep learning model to solve robust optimization problems. The majority of existing studies on deep learning focus on the model learning capability, while assuming the…

Edge AI model deployment is a multi-stage engineering process involving model conversion, operator compatibility handling, quantization calibration, runtime integration, and accuracy validation. In practice, this workflow is long,…

Modern AI systems are typically developed through multiple stages-pretraining, fine-tuning rounds, and subsequent adaptation or alignment, where each stage builds on the previous ones and updates the model in distinct ways. This raises a…

This paper describes a possible way to improve computer security by implementing a program which implements the following three features related to a weak notion of artificial consciousness: (partial) self-monitoring, ability to compute the…

AI predictive systems are increasingly embedded in decision making pipelines, shaping high stakes choices once made solely by humans. Yet robust decisions under uncertainty still rely on capabilities that current AI lacks: domain knowledge…

Artificial Intelligence (AI) has become an integral part of modern-day security solutions for its ability to learn very complex functions and handling "Big Data". However, the lack of explainability and interpretability of successful AI…

Environment perception is the task for intelligent vehicles on which all subsequent steps rely. A key part of perception is to safely detect other road users such as vehicles, pedestrians, and cyclists. With modern deep learning techniques…

Modern autonomous systems with machine learning components often use uncertainty quantification to help produce assurances about system operation. However, there is a lack of consensus in the community on what uncertainty is and how to…

Open-source is frequently described as a driver for unprecedented communication and collaboration, and the process works best when projects support teamwork. Yet, open-source cooperation processes in no way protect project contributors from…

Neural networks (NNs) lack measures of "reliability" estimation that would enable reasoning over their predictions. Despite the vital importance, especially in areas of human well-being and health, state-of-the-art uncertainty estimation…

Artificial intelligence systems are now deployed at scale across sectors, accompanied by a growing number of real-world incidents ranging from misinformation and cybercrime to autonomous-system failures. Databases of AI incidents index…

While the increased use of AI in the manufacturing sector has been widely noted, there is little understanding on the risks that it may raise in a manufacturing organisation. Although various high level frameworks and definitions have been…

With the increasing scale, complexity, and heterogeneity of the next generation networked systems, seamless control, management, and security of such systems becomes increasingly challenging. Many diverse applications have driven interest…

Intrusion detection poses a significant challenge within expansive and persistently interconnected environments. As malicious code continues to advance and sophisticated attack methodologies proliferate, various advanced deep learning-based…

This chapter bridges technical analysis and organizational preparedness by tracing the path from layered failure modes to reliability awareness in generative and agentic AI systems. We first introduce an 11-layer failure stack, a structured…

Trust is a fundamental concept in many real-world applications such as e-commerce and peer-to-peer networks. In these applications, users can generate local opinions about the counterparts based on direct experiences, and these opinions can…

AI deployed in the real-world should be capable of autonomously adapting to novelties encountered after deployment. Yet, in the field of continual learning, the reliance on novelty and labeling oracles is commonplace albeit unrealistic.…

Uncertainty quantification is essential for the reliable deployment of machine learning models to high-stakes application domains. Uncertainty quantification is all the more challenging when training distribution and test distribution are…

In this paper we argue that, to its detriment, transparency research overlooks many foundational concepts of artificial intelligence. As an illustrating example we focus on uncertainty quantification in the context of counterfactual…

The promise of AI is huge. AI systems have already achieved good enough performance to be in our streets and in our homes. However, they can be brittle and unfair. For society to reap the benefits of AI systems, society needs to be able to…