相关论文: Test Input Validation for Vision-based DL Systems:…

A conceptual model is used to support development and design within the area of systems and software modeling. The notion of validation refers to representing a domain in a model accurately and generating results using an executable model.…

Deep learning (DL) has proven to be a highly effective approach for developing models in diverse contexts, including visual perception, speech recognition, and machine translation. However, the end-to-end process for applying DL is not…

Large Vision-Language Models (LVLMs) exhibit outstanding performance on vision-language tasks but struggle with hallucination problems. Through in-depth analysis of LVLM activation patterns, we reveal two key findings: 1) truthfulness and…

The automation of the medical evidence acquisition and diagnosis process has recently attracted increasing attention in order to reduce the workload of doctors and democratize access to medical care. However, most works proposed in the…

As deep learning models are widely used in software systems, test generation plays a crucial role in assessing the quality of such models before deployment. To date, the most advanced test generators rely on generative AI to synthesize…

Deep learning (DL) approaches are state-of-the-art for many medical image segmentation tasks. They offer a number of advantages: they can be trained for specific tasks, computations are fast at test time, and segmentation quality is…

Deep Learning (DL) techniques are now widespread and being integrated into many important systems. Their classification and recognition abilities ensure their relevance for multiple application domains. As machine-learning that relies on…

Machine learning methods may have the potential to significantly accelerate drug discovery. However, the increasing rate of new methodological approaches being published in the literature raises the fundamental question of how models should…

Much effort is being made by the researchers in order to detect and diagnose diabetic retinopathy (DR) accurately automatically. The disease is very dangerous as it can cause blindness suddenly if it is not continuously screened. Therefore,…

Pretrained on web-scale open data, VLMs offer powerful capabilities for solving downstream tasks after being adapted to task-specific labeled data. Yet, data labeling can be expensive and may demand domain expertise. Active Learning (AL)…

Deep learning models for object detection in autonomous driving have recently achieved impressive performance gains and are already being deployed in vehicles worldwide. However, current models require increasingly large datasets for…

As the adoption of Deep Learning (DL) systems continues to rise, an increasing number of approaches are being proposed to test these systems, localise faults within them, and repair those faults. The best attestation of effectiveness for…

In this dissertation, we investigated and enhanced Deep Learning (DL) techniques for counting objects, like pedestrians, cells or vehicles, in still images or video frames. In particular, we tackled the challenge related to the lack of data…

We review state-of-the-art formal methods applied to the emerging field of the verification of machine learning systems. Formal methods can provide rigorous correctness guarantees on hardware and software systems. Thanks to the availability…

In recent years, deep reinforcement learning (DRL) approaches have generated highly successful controllers for a myriad of complex domains. However, the opaque nature of these models limits their applicability in aerospace systems and…

Intrusion detection has been a commonly adopted detective security measures to safeguard systems and networks from various threats. A robust intrusion detection system (IDS) can essentially mitigate threats by providing alerts. In networks…

Deep learning (DL) plays a key role in autonomous driving systems. DL models support perception modules, equipped with tasks such as object detection and sensor fusion. These DL models enable vehicles to process multi-sensor inputs to…

Vision-language Models (VLMs), despite achieving strong performance on multimodal benchmarks, often misinterpret straightforward visual concepts that humans identify effortlessly, such as counting, spatial reasoning, and viewpoint…

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across multimodal tasks such as visual perception and reasoning, leading to good performance on various multimodal evaluation benchmarks. However, these…

Large Vision-Language Models (VLMs) have achieved remarkable performance across a wide range of tasks. However, their deployment in safety-critical domains poses significant challenges. Existing safety fine-tuning methods, which focus on…