Related papers: How is a gas sensor poisoned by volatile methylsil…
Adversarial machine learning has attracted a great amount of attention in recent years. In a poisoning attack, the adversary can inject a small number of specially crafted samples into the training data which make the decision boundary…
AI-Based Safety-Critical Systems (AI-SCS) are being increasingly deployed in the real world. These can pose a risk of harm to people and the environment. Reducing that risk is an overarching priority during development and operation. As…
The rapid advancement and deployment of AI systems have created an urgent need for standard safety-evaluation frameworks. This paper introduces AILuminate v1.0, the first comprehensive industry-standard benchmark for assessing AI-product…
Vision-Language Models (VLMs) have garnered significant attention for their remarkable ability to interpret and generate multimodal content. However, securing these models against jailbreak attacks continues to be a substantial challenge.…
Flawed planning from VLM-driven embodied agents poses significant safety hazards, hindering their deployment in real-world household tasks. However, existing static, non-interactive evaluation paradigms fail to adequately assess risks…
Embedding artificial intelligence into systems introduces significant challenges to modern engineering practices. Hazard analysis tools and processes have not yet been adequately adapted to the new paradigm. This paper describes initial…
Asthma is a chronic disease of the airways of the lungs. It results in inflammation and narrowing of the respiratory passages, which prevents air flow into the airways and leads to frequent bouts of shortness of breath with wheezing…
The need for analysis of toxicity in new drug candidates and the requirement of doing it fast have asked the consideration of scientists towards the use of artificial intelligence tools to examine toxicity levels and to develop models to a…
AI scientists powered by large language models have demonstrated substantial promise in autonomously conducting experiments and facilitating scientific discoveries across various disciplines. While their capabilities are promising, these…
Hypothesis: Surfactants are often added to aqueous solutions to induce spreading on otherwise unwettable hydrophobic surfaces. Alternatively, they can be introduced directly into solid hydrophobic materials-such as the soft elastomer,…
One of the most important parts of business, especially in the coal mining sector, is industrial safety. Suffocation, gas poisoning, object falls, roof collapses, and gas explosions are among the risks associated with underground mining.…
Large Vision Language Models (LVLMs) demonstrate strong capabilities in multimodal reasoning and many real-world applications, such as visual question answering. However, LVLMs are highly vulnerable to jailbreaking attacks. This paper…
AI-based code generators have become pivotal in assisting developers in writing software starting from natural language (NL). However, they are trained on large amounts of data, often collected from unsanitized online sources (e.g., GitHub,…
To increase the scientific output of particle physics experiments, upgrades are underway at all major accelerator facilities to significantly improve the luminosity. Consequently, the solid-state detectors used in the experiments will…
The increasing integration of AI agents into cyber-physical systems (CPS) introduces new security risks that extend beyond traditional cyber or physical threat models. Recent advances in generative AI enable deepfake and semantic…
The rapid advancement of machine learning and artificial intelligence (AI)-driven techniques is revolutionizing materials discovery, property prediction, and material design by minimizing human intervention and accelerating scientific…
Language-conditioned robotic manipulation in open-world settings requires not only accurate task execution but also the ability to detect failures for robust deployment in real-world environments. Although recent advances in vision-language…
Sensors (e.g., light, gyroscope, accelerometer) and sensing-enabled applications on a smart device make the applications more user-friendly and efficient. However, the current permission-based sensor management systems of smart devices only…
Volcanic gas emissions are key precursors of eruptive activity. Yet, obtaining accurate near-surface measurements remains hazardous and logistically challenging, motivating the need for autonomous solutions. Limited mobility in rough…
In this contribution we discuss how to prepare some possible detectors - only silicon option being considered, for the new era of HEP challenges because the bulk displacement damage in the detector, consequence of irradiation, produces…