1 citations · 1 across the 4 of their papers we have counts for
Showing cs.CRShow all
2 papers · 1 filter
cs.CR2025
DRIP: Defending Prompt Injection via Token-wise Representation Editing and Residual Instruction Fusion
Ruofan Liu, Yun Lin, Zhiyong Huang +1
Large language models (LLMs) are increasingly integrated into IT infrastructures, where they process user data according to predefined instructions. However, conventional LLMs rema…
cs.CR2025
PiMRef: Deducing Ever-evolving Spear-phishing Emails with Knowledge Base Invariants
Ruofan Liu, Yun Lin, Yuxin Wang +5
Phishing email is a critical step in the cybercrime kill chain due to the high reachability of victims' email accounts and the low cost of launching phishing campaigns. This ever-e…