Image de couverture de livre

Towards Assurance of LLM Adversarial Robustness using Ontology-Driven Argumentation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Momcilovic, Tomas Bueno, Buesser, Beat, Zizzo, Giulio, Purcell, Mark, Balta, Dian
Format:	Preprint
Publié:	2024
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Developing Assurance Cases for Adversarial Robustness and Regulatory Compliance in LLMs
par: Momcilovic, Tomas Bueno, et autres
Publié: (2024)

Towards Assuring EU AI Act Compliance and Adversarial Robustness of LLMs
par: Momcilovic, Tomas Bueno, et autres
Publié: (2024)

Knowledge-Augmented Reasoning for EUAIA Compliance and Adversarial Robustness of LLMs
par: Momcilovic, Tomas Bueno, et autres
Publié: (2024)

OntoGSN: An Ontology-Based Framework for Semantic Management and Extension of Assurance Cases
par: Momcilovic, Tomas Bueno, et autres
Publié: (2025)

Towards a Practical Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via Randomized Smoothing
par: Gibert, Daniel, et autres
Publié: (2023)

A Robust Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via (De)Randomized Smoothing
par: Gibert, Daniel, et autres
Publié: (2024)

Attack Atlas: A Practitioner's Perspective on Challenges and Pitfalls in Red Teaming GenAI
par: Rawat, Ambrish, et autres
Publié: (2024)

Autonomy and Agency in Agentic AI: Architectural Tactics for Regulated Contexts
par: Safin, Damir, et autres
Publié: (2026)

MoJE: Mixture of Jailbreak Experts, Naive Tabular Classifiers as Guard for Prompt Attacks
par: Cornacchia, Giandomenico, et autres
Publié: (2024)

Certified Adversarial Robustness of Machine Learning-based Malware Detectors via (De)Randomized Smoothing
par: Gibert, Daniel, et autres
Publié: (2024)

Adversarial Prompt Evaluation: Systematic Benchmarking of Guardrails Against Prompt Input Attacks on LLMs
par: Zizzo, Giulio, et autres
Publié: (2025)

Blue Teaming Function-Calling Agents
par: Dolcetti, Greta, et autres
Publié: (2026)

Step-Tagging: Toward controlling the generation of Language Reasoning Models through step monitoring
par: Belkhiter, Yannis, et autres
Publié: (2025)

Defeaters and Eliminative Argumentation in Assurance 2.0
par: Bloomfield, Robin, et autres
Publié: (2024)

How Worst-Case Are Adversarial Attacks? Linking Adversarial and Perturbation Robustness
par: Rossolini, Giulio
Publié: (2026)

Regularized Q-Learning with Linear Function Approximation
par: Xi, Jiachen, et autres
Publié: (2024)

Towards a Cyber Information Ontology
par: Limbaugh, David, et autres
Publié: (2024)

LOGicalThought: Logic-Based Ontological Grounding of LLMs for High-Assurance Reasoning
par: Nananukul, Navapat, et autres
Publié: (2025)

LLM-Driven Ontology Construction for Enterprise Knowledge Graphs
par: Oyewale, Abdulsobur, et autres
Publié: (2026)

Assessing the Impact of Packing on Machine Learning-Based Malware Detection and Classification Systems
par: Gibert, Daniel, et autres
Publié: (2024)

Justified Evidence Collection for Argument-based AI Fairness Assurance
par: Sabuncuoglu, Alpay, et autres
Publié: (2025)

Pre-Hoc Predictions in AutoML: Leveraging LLMs to Enhance Model Selection and Benchmarking for Tabular datasets
par: Belkhiter, Yannis, et autres
Publié: (2025)

Rashomon Memory: Towards Argumentation-Driven Retrieval for Multi-Perspective Agent Memory
par: Sadowski, Albert, et autres
Publié: (2026)

Towards Robust Argumentative Essay Understanding via TIDE: An Interactive Framework with Trial and Debate
par: Yin, Zheqin, et autres
Publié: (2026)

Towards Complex Ontology Alignment using Large Language Models
par: Amini, Reihaneh, et autres
Publié: (2024)

Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models
par: Belkhiter, Yannis, et autres
Publié: (2026)

Towards an Ontology of Traceable Impact Management in the Food Supply Chain
par: Gajderowicz, Bart, et autres
Publié: (2025)

Are Robust LLM Fingerprints Adversarially Robust?
par: Nasery, Anshul, et autres
Publié: (2025)

Wasserstein Distributionally Robust Bayesian Optimization with Continuous Context
par: Micheli, Francesco, et autres
Publié: (2025)

Towards Automated Ontology Generation from Unstructured Text: A Multi-Agent LLM Approach
par: Talukder, Abid, et autres
Publié: (2026)

Differentially Private and Adversarially Robust Machine Learning: An Empirical Evaluation
par: Thakkar, Janvi, et autres
Publié: (2024)

Adversarial Preference Learning for Robust LLM Alignment
par: Wang, Yuanfu, et autres
Publié: (2025)

TurboEvolve: Towards Fast and Robust LLM-Driven Program Evolution
par: Yang, Yang, et autres
Publié: (2026)

Towards Continuous Assurance with Formal Verification and Assurance Cases
par: Abeywickrama, Dhaminda B., et autres
Publié: (2025)

Towards Adversarially Robust Deep Metric Learning
par: Ke, Xiaopeng
Publié: (2025)

LLM-based Argument Mining meets Argumentation and Description Logics: a Unified Framework for Reasoning about Debates
par: Alfano, Gianvincenzo, et autres
Publié: (2026)

From Ontology Conformance to Admissible Reconfiguration: A RoSO/SMGI Adequacy Argument for Robotic Service Governance
par: Osmani, Aomar
Publié: (2026)

We Argue to Agree: Towards Personality-Driven Argumentation-Based Negotiation Dialogue Systems for Tourism
par: Priya, Priyanshu, et autres
Publié: (2025)

OntoMetric: An Ontology-Driven LLM-Assisted Framework for Automated ESG Metric Knowledge Graph Generation
par: Yu, Mingqin, et autres
Publié: (2025)

Towards Robust Training Datasets for Machine Learning with Ontologies: A Case Study for Emergency Road Vehicle Detection
par: Vonderhaar, Lynn, et autres
Publié: (2024)