Natalia Pérez-Campanero Antolín

According to our database, Natalia Pérez-Campanero Antolín authored at least 6 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2025

The Steganographic Potentials of Language Models.

Artem Karpov, Tinuade Adeleke, Seong Hah Cho, Natalia Pérez-Campanero

CoRR, May, 2025

Self-Ablating Transformers: More Interpretability, Less Sparsity.

Jeremias Ferrao, Luhan Mikaelson, Keenan Pepper, Natalia Pérez-Campanero Antolín

CoRR, May, 2025

Latent Adversarial Training Improves the Representation of Refusal.

Alexandra Abbas, Nora Petrova, Helios Ael Lyons, Natalia Pérez-Campanero

CoRR, April, 2025

Deceptive Automated Interpretability: Language Models Coordinating to Fool Oversight Systems.

Simon Lermen, Mateusz Dziemian, Natalia Pérez-Campanero Antolín

CoRR, April, 2025

Identifying Cooperative Personalities in Multi-agent Contexts through Personality Steering with Representation Engineering.

Kenneth J. K. Ong, Lye Jia Jun, Hieu Minh, Seong Hah Cho, Natalia Pérez-Campanero Antolín

CoRR, March, 2025

2024

CryptoFormalEval: Integrating LLMs and Formal Verification for Automated Cryptographic Protocol Vulnerability Detection.

Cristian Curaba, Denis D'Ambrosi, Alessandro Minisini, Natalia Pérez-Campanero Antolín

CoRR, 2024