19 citations · 40 across the 12 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.CR2026
Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training
Qiusi Zhan, Nian Lyu, Stephanie Ding +5
Developers can build LLM agents by adapting third-party models through benign post-training. We study a supply-chain threat in which an attacker supplies a model with a backdoor: h…
cs.AI2026
Securing Multimodal AI through Internal Information Decomposition
Jehyeok Yeon, Hyeonjeong Ha, Qiusi Zhan +1
Multimodal large language models introduce attack surfaces absent in unimodal systems: adversaries can distribute malicious intent across modalities to evade unimodal safeguards. T…