From the 1 of 4 linked papers with an AI index.
4 papers
MaxSAT-Based Feedback for Guiding Vision-Language Models in Sudoku
Pedro Orvalho, Guillem AlenyÃ, Felip ManyÃ
The paper introduces a neuro‑symbolic method that uses a MaxSAT solver to check and refine the outputs of vision‑language models when solving Sudoku, providing feedback that improv…
Reliable Reasoning with Large Language Models via Preference-Based Maximum Satisfiability
Pedro Orvalho, Marta Kwiatkowska, Guillem Alenyà +1
Large Language Models (LLMs) excel at understanding natural language but struggle with optimisation tasks involving multiple constraints and user-defined preferences, which commonl…
ByteShield: Adversarially Robust End-to-End Malware Detection through Byte Masking
Daniel Gibert, Felip ManyÃ
Research has proven that end-to-end malware detectors are vulnerable to adversarial attacks. In response, the research community has proposed defenses based on randomized and (de)r…
DeepTrust: Multi-Step Classification through Dissimilar Adversarial Representations for Robust Android Malware Detection
Daniel Pulido-Cortázar, Daniel Gibert, Felip ManyÃ
Over the last decade, machine learning has been extensively applied to identify malicious Android applications. However, such approaches remain vulnerable against adversarial examp…