Pengzhou Cheng
7 papers · 2023–2026 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Interdisciplinary Bridge π Conference Polyglot (5) π Cross-Pollinator (12) π Renaissance Researcher (5) πΊοΈ Taxonomy Completionist (14)
π§
Keyword Pioneer
Conferences
AAAI (2)
ACL (2)
COLING (1)
EMNLP (1)
NAACL (1)
Top co-authors
Research topics
Keywords
backdoor attack
(3)
frequency space
(2)
multimodal large language model
(2)
gui agent
(2)
contrastive learning
(2)
gaussian mixture model
(1)
language model
(1)
low-rank adaptation
(1)
out-of-distribution detection
(1)
intellectual property protection
(1)
ownership verification
(1)
pre-trained language model
(1)
ood detection
(1)
min-max optimization
(1)
contrastive loss
(1)
agent system
(1)
generative language model
(1)
gradient clustering
(1)
confidence prediction
(1)
model watermarking
(1)
Papers
GEM: Gaussian Embedding Modeling for Out-of-Distribution Detection in GUI Agents
AAAI 2026
OS-Kairos: Adaptive Interaction for MLLM-Powered GUI Agents
ACL 2025
Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining
COLING 2025
Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents
EMNLP 2025
SynGhost: Invisible and Universal Task-agnostic Backdoor Attack via Syntactic Transfer
NAACL 2025
Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space
ACL 2024
PLMmark: A Secure and Robust Black-Box Watermarking Framework for Pre-trained Language Models
AAAI 2023