Pengyu Zhu
3 papers · 2025–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Top co-authors
Research topics
Keywords
large language model
(2)
instruction following
(1)
backdoor attack
(1)
adversarial attack
(1)
supervised fine-tuning
(1)
jailbreak attack
(1)
data synthesis
(1)
prompt injection
(1)
llm agent
(1)
dynamic encryption
(1)
safety audit
(1)
multi-backdoor implantation
(1)
sub-backdoor fragment
(1)
reinforcement learning
(1)
contextual priming
(1)