Abstract. Large language models (LLMs) are increasingly considered for deployment as the control component of robotic health attendants (RHAs), yet their s

This study provides an analytical foundation for adversarial synchronization control in Kuramoto oscillator networks, where small gradient-based perturbations a

Size matters when it comes to AI morality A Japanese scientist says artificial intelligence (AI) becomes more aligned with human moral reasoning the larger and more complex it gets. He&nbs

Abstract. Autonomous systems increasingly require moral judgement capabilities, yet whether these capabilities scale predictably with model size remains un

This study provides an analytical foundation for adversarial synchronization control in Kuramoto oscillator networks, where small gradient-based perturbations applied repeatedly to oscillator phases c...

Large language models (LLMs) are increasingly considered for deployment as the control component of robotic health attendants, yet their safety in this context remains poorly characterized. We introdu...

Large language models (LLMs) are increasingly considered for deployment as the control component of robotic health attendants, yet their safety in this context remains poorly characterized. We introdu...

Accurate identification of freshwater microalgae is critical for early detection of harmful algal blooms, water quality monitoring, and sustainable bi…

Accurate identification of freshwater microalgae is critical for early detection of harmful algal blooms, water quality monitoring, and sustainable bi…

Autonomous systems increasingly require moral judgment capabilities, yet whether these capabilities scale predictably with model size remains unexplored. We systematically evaluate 75 large language m...

Autonomous systems increasingly require moral judgment capabilities, yet whether these capabilities scale predictably with model size remains unexplored. We systematically evaluate 75 large language m...

We report results from a large-scale, laboratory-style experiment in which a Large Language Model (LLM)-represented by three versions of ChatGPT-3.5-turbo-makes

This study investigates perturbation strategies inspired by adversarial attack principles from deep learning, designed to control synchronization dynamics throu

This study investigates perturbation strategies inspired by adversarial attack principles from deep learning, designed to control synchronization dynamics throu

Welche Chancen bietet Künstliche Intelligenz für das Stau-Land NRW? Kann KI dafür sorgen, dass wir schneller und sicher ankommen – oder wenigstens bequemer? Moderatorin Catherine Vogel untersucht, wi...

Welche Chancen bietet Künstliche Intelligenz für das Stau-Land NRW? Kann KI dafür sorgen, dass wir schneller und sicher ankommen – oder wenigstens bequemer? Moderatorin Catherine Vogel untersucht, wi...

Das autonom fahrende Auto ist längst in der Entwicklung. Wie entscheidet die KI bei einem Autounfall, wer überlebt und wer nicht?

AI apps that can detect skin cancer can be manipulated and potentially miss cases of melanoma, a serious skin cancer.

AI apps that can detect skin cancer can be manipulated and potentially miss cases of melanoma, a serious skin cancer.

This study investigates adversarial attacks, a concept from deep learning, designed to control synchronization dynamics through strategically crafted minimal perturbations. We propose a gradient-based...

This study investigates adversarial attacks, a concept from deep learning, designed to control synchronization dynamics through strategically crafted minimal perturbations. We propose a gradient-based...

Scientific Reports - Mobile applications for skin cancer detection are vulnerable to physical camera-based adversarial attacks

The rapid advancement of Large Language Models (LLMs) and their potential integration into autonomous driving systems necessitates understanding their moral decision-making capabilities. While our pre...

Ecosystems are often represented as networks. The structure and function of ecological networks are significant in ecology. The availability of ecolog…

Ecosystems are often represented as networks. The structure and function of ecological networks are significant in ecology. The availability of ecolog…

Skin cancer is one of the most prevalent malignant tumors, and early detection is crucial for patient prognosis, leading to the development of mobile applications as screening tools. Recent advances i...

Skin cancer is one of the most prevalent malignant tumors, and early detection is crucial for patient prognosis, leading to the development of mobile applications as screening tools. Recent advances i...

令和7年度科学技術分野の文部科学大臣表彰受賞者の決定等についてのページです。

Scientific Reports - Mitigating opinion polarization in social networks using adversarial attacks

Scientific Reports - Mitigating opinion polarization in social networks using adversarial attacks

In recent years, Large Language Models have attracted growing interest for their significant potential, though concerns have rapidly emerged regarding unsafe behaviors stemming from inherent stereotyp...

UNCHAIN prompthehack Project