Julius Broomfield

According to our database, Julius Broomfield authored at least 5 papers between 2024 and 2025.

Collaborative distances:

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

2025

Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility.

Brendan Murphy, Dillon Bowen, Shahrad Mohammadzadeh, Julius Broomfield, Adam Gleave, Kellin Pelrine

CoRR, July, 2025

A Thousand Words or An Image: Studying the Influence of Persona Modality in Multimodal LLMs.

Julius Broomfield, Kartik Sharma, Srijan Kumar

CoRR, February, 2025

Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility.

Brendan Murphy, Dillon Bowen, Shahrad Mohammadzadeh, Tom Tseng, Julius Broomfield, Adam Gleave, Kellin Pelrine

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

The Structural Safety Generalization Problem.

Julius Broomfield, Tom Gibbs, George Ingebretsen, Ethan Kosak-Hine, Tia Nasir, Jason Zhang, Reihaneh Iranmanesh, Sara Pieri, Reihaneh Rabbany, Kellin Pelrine

Proceedings of the Findings of the Association for Computational Linguistics, 2025

2024

Emerging Vulnerabilities in Frontier Models: Multi-Turn Jailbreak Attacks.

Tom Gibbs, Ethan Kosak-Hine, George Ingebretsen, Jason Zhang, Julius Broomfield, Sara Pieri, Reihaneh Iranmanesh, Reihaneh Rabbany, Kellin Pelrine

CoRR, 2024