Defending LLMs against jailbreak attacks through representation offset detection

Shuo Liu, Xiang Cheng 0003, ZhenZhong Zheng, Sen Su. Defending LLMs against jailbreak attacks through representation offset detection. Inf. Process. Manage., 63(5):104662, 2026. [doi]

References

No references recorded for this publication.

Cited by

No citations of this publication recorded.