Related papers: Attention Misses Visual Risk: Risk-Adaptive Steeri…

Large Vision-Language Models (LVLMs) rely on attention-based retrieval of safety instructions to maintain alignment during generation. Existing attacks typically optimize image perturbations to maximize harmful output likelihood, but suffer…

Maritime environments often present hazardous situations due to factors such as moving ships or buoys, which become obstacles under the influence of waves. In such challenging conditions, the ability to detect and track potentially…

Driver distraction remains a leading cause of road traffic accidents, contributing to thousands of fatalities annually across the globe. While deep learning-based driver activity recognition methods have shown promise in detecting such…

Predicting stroke risk is a complex challenge that can be enhanced by integrating diverse clinically available data modalities. This study introduces a self-supervised multimodal framework that combines 3D brain imaging, clinical data, and…

Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data, thereby introducing new dimensions of potential attacks and complex risk combinations. In this paper, we begin with…

The Critical View of Safety (CVS) is crucial for safe laparoscopic cholecystectomy, yet assessing CVS criteria remains a complex and challenging task, even for experts. Traditional models for CVS recognition depend on vision-only models…

Ensuring the safety and harmlessness of Large Language Models (LLMs) has become equally critical as their performance in applications. However, existing safety alignment methods typically suffer from safety-performance trade-offs and the…

Safe navigation of drones in the presence of adversarial physical attacks from multiple pursuers is a challenging task. This paper proposes a novel approach, asynchronous multi-stage deep reinforcement learning (AMS-DRL), to train…

Vision-language models (VLMs) are increasingly deployed in real-world and embodied settings where safety decisions depend on visual context. However, it remains unclear which visual evidence drives these judgments. We study whether…

The increasing use of Machine Learning (ML) components embedded in autonomous systems -- so-called Learning-Enabled Systems (LESs) -- has resulted in the pressing need to assure their functional safety. As for traditional functional safety,…

Safe exploration is critical for using reinforcement learning (RL) in risk-sensitive environments. Recent work learns risk measures which measure the probability of violating constraints, which can then be used to enable safety. However,…

In safety-critical domains like automated driving (AD), errors by the object detector may endanger pedestrians and other vulnerable road users (VRU). As common evaluation metrics are not an adequate safety indicator, recent works employ…

Underwater robotic vision encounters significant challenges, necessitating advanced solutions to enhance performance and adaptability. This paper presents MARS (Multi-Scale Adaptive Robotics Vision), a novel approach to underwater object…

LiDAR-based 3D perception and localization on unmanned aerial vehicles (UAVs) are fundamentally limited by the narrow field of view (FoV) of compact LiDAR sensors and the payload constraints that preclude multi-sensor configurations.…

Vision-language models (VLMs), which process image and text inputs, are increasingly integrated into chat assistants and other consumer AI applications. Without proper safeguards, however, VLMs may give harmful advice (e.g. how to…

There has been a plethora of work towards improving robot perception and navigation, yet their application in hazardous environments, like during a fire or an earthquake, is still at a nascent stage. We hypothesize two key challenges here:…

Multimodal deep learning, especially vision-language models, have gained significant traction in recent years, greatly improving performance on many downstream tasks, including content moderation and violence detection. However, standard…

Reinforcement learning (RL) has shown great potential for solving complex tasks in a variety of domains. However, applying RL to safety-critical systems in the real-world is not easy as many algorithms are sample-inefficient and maximising…

Multimodal Large Language Models (MLLMs) often exhibit significant modality preference, which is a tendency to favor one modality over another. Depending on the input, they may over-rely on linguistic priors relative to visual evidence, or…

While the most visible part of the safety verification process of automated vehicles concerns the planning and control system, it is often overlooked that safety of the latter crucially depends on the fault-tolerance of the preceding…