5 papers
Keep Calm and Avoid Harmful Content: Concept Alignment and Latent Manipulation Towards Safer Answers
Ruben Belo, Marta Guimaraes, Claudia Soares
Large Language Models are susceptible to jailbreak attacks that bypass built-in safety guardrails (e.g., by tricking the model with adversarial prompts). We propose Concept Alignme…
One-Shot Initial Orbit Determination in Low-Earth Orbit
Ricardo Ferreira, Marta Guimarães, Filipa Valdeira +1
Due to the importance of satellites for society and the exponential increase in the number of objects in orbit, it is important to accurately determine the state (e.g., position an…
Conjunction Data Messages for Space Collision Behave as a Poisson Process
Francisco Caldas, Cláudia Soares, Cláudia Nunes +1
Space debris is a major problem in space exploration. International bodies continuously monitor a large database of orbiting objects and emit warnings in the form of conjunction da…
Decision Support Models for Predicting and Explaining Airport Passenger Connectivity from Data
Marta Guimaraes, Claudia Soares, Rodrigo Ventura
Predicting if passengers in a connecting flight will lose their connection is paramount for airline profitability. We present novel machine learning-based decision support models f…
Conjunction Data Messages behave as a Poisson Process
Francisco Caldas, Claudia Soares, Cláudia Nunes +3
Space debris is a major problem in space exploration. International bodies continuously monitor a large database of orbiting objects and emit warnings in the form of conjunction da…