James Beetham

According to our database, James Beetham authored at least 5 papers between 2022 and 2026.

Collaborative distances:

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

2026

Jailbreaks as Inference-Time Alignment: A Framework for Understanding Safety Failures in LLMs.

James Beetham, Souradip Chakraborty, Mengdi Wang, Furong Huang, Amrit Singh Bedi, Mubarak Shah

Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics, 2026

SafeR-CLIP: Mitigating NSFW Content in Vision-Language Models While Preserving Pre-Trained Knowledge.

Adeel Yousaf, Joseph Fioresi, James Beetham, Amrit Singh Bedi, Mubarak Shah

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2024

LIAR: Leveraging Alignment (Best-of-N) to Jailbreak LLMs in Seconds.

James Beetham, Souradip Chakraborty, Mengdi Wang, Furong Huang, Amrit Singh Bedi, Mubarak Shah

CoRR, 2024

2023

Dual Student Networks for Data-Free Model Stealing.

James Beetham, Navid Kardan, Ajmal Saeed Mian, Mubarak Shah

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Detecting Compromised Architecture/Weights of a Deep Model.

James Beetham, Navid Kardan, Ajmal Mian, Mubarak Shah

Proceedings of the 26th International Conference on Pattern Recognition, 2022