Kaiyang Ji

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Natural Language Processing (1)Red-Teaming & Adversarial Robustness (1)

Frequent co-authors

Linghan Chen (1)Yudong Gao (1)Jiyao Wang (1)Kaiyan Ji (1)

Papers (1)

Aug 25, 2026

Linghan Chen +53d ago·also Affiliation:

Do System Prompts Leave Behavioral Fingerprints? A Large-Scale Empirical Study of Clone Detection via Output Similarity

Cloned outputs from LLMs can be detected with over 87% accuracy using behavioral signatures, revealing significant vulnerabilities in prompt security.

Linghan Chen, Yudong Gao, Jiyao Wang +3

Natural Language Processing Red-Teaming & Adversarial Robustness

Search

Kaiyang Ji

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)