Peizhuo Lv
4 papers · 2024–2026 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌈
Renaissance Researcher
(5)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
AAAI (2)
ACL (2)
Top co-authors
Research topics
Keywords
system prompt
(2)
backdoor attack
(1)
diffusion model
(1)
poisoning attack
(1)
forward process
(1)
reasoning trace
(1)
black-box verification
(1)
context extraction
(1)
model watermarking
(1)
large language model
(1)
prompt leakage
(1)
dataset sanitization
(1)
trigger feature
(1)
poisoned dataset
(1)
trigger removal
(1)
prompt fingerprinting
(1)
first token response
(1)
adversarial instruction
(1)
llm app cloning
(1)
model security
(1)
Papers
PROMPRINT: Prompt Fingerprinting via First-Token Response for LLM App Cloning Detection
ACL 2026
ReasMark: A Robust Watermark for Attributing LLM Reasoning Under Knowledge Distillation Attacks
ACL 2026
RepeatLeakage: Leak Prompts from Repeating as Large Language Model Is a Good Repeater
AAAI 2025
DataElixir: Purifying Poisoned Dataset to Mitigate Backdoor Attacks via Diffusion Models
AAAI 2024