Zhengyuan Jiang
6 papers · 2024–2026 · 5 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 · Silver
🌉
Interdisciplinary Bridge · Gold
🗺️
Taxonomy Completionist
(15)
🌈
Renaissance Researcher
(6)
Venues
Top co-authors
Research topics
Artificial Intelligence
(3)
Core AI
(3)
Deep Learning
(2)
Machine Learning
(2)
Computer Science
(1)
Healthcare & Medicine
(1)
Natural Language Processing
(1)
Security & Privacy
(1)
Speech & Audio
(1)
Analysis
(1)
Applications · Natural Language Processing
(1)
Applications · Computer Science
(1)
Architectures
(1)
Clinical
(1)
Learning Types
(1)
Keywords
adversarial perturbation
(2)
large language model
(2)
speech synthesis
(1)
prompt engineering
(1)
audio watermarking
(1)
synthetic speech detection
(1)
perturbation robustness
(1)
text-to-image model
(1)
evasion attack
(1)
watermark detection
(1)
jailbreak attack
(1)
adversarial prompt
(1)
robustness evaluation
(1)
prompt injection
(1)
transfer attack
(1)
statistical guarantee
(1)
clinical text classification
(1)
safety guardrail
(1)
synthetic speech
(1)
robustness benchmark
(1)
Papers
Fingerprinting LLMs via Prompt Injection
ACL 2026
Jailbreaking Safeguarded Text-to-Image Models via Large Language Models
EACL 2026
Learning from Textual Radiology Reports: A Benchmark Dataset for Coronary CT Angiography
ACL 2026
A Transfer Attack to Image Watermarks
ICLR 2025
AudioMarkBench: Benchmarking Robustness of Audio Watermarking
NeurIPS 2024
Certifiably Robust Image Watermark
ECCV 2024