Kai Williams

According to our database, Kai Williams authored at least 5 papers between 2024 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Password-Activated Shutdown Protocols for Misaligned Frontier Agents.

Kai Williams, Rohan Subramani, Francis Rhys Ward

CoRR, December, 2025

2024

Representation noising effectively prevents harmful fine-tuning on LLMs.

Domenic Rosati, Jan Wehner, Kai Williams, Lukasz Bartoszcze, David Atanasov, Robie Gonzales, Subhabrata Majumdar, Carsten Maple, Hassan Sajjad, Frank Rudzicz

CoRR, 2024

Immunization against harmful fine-tuning attacks.

Domenic Rosati, Jan Wehner, Kai Williams, Lukasz Bartoszcze, Jan Batzner, Hassan Sajjad, Frank Rudzicz

CoRR, 2024

Representation Noising: A Defence Mechanism Against Harmful Finetuning.

Domenic Rosati, Jan Wehner, Kai Williams, Lukasz Bartoszcze, Robie Gonzales, Carsten Maple, Subhabrata Majumdar, Hassan Sajjad, Frank Rudzicz

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Immunization against harmful fine-tuning attacks.

Domenic Rosati, Jan Wehner, Kai Williams, Lukasz Bartoszcze, Hassan Sajjad, Frank Rudzicz

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2024, 2024