Zhiyuan Chang
6 papers · 2024–2026 · 2 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 · Silver
🗺️
Taxonomy Completionist
(17)
🏆
Keyword Champion
Top co-authors
Research topics
Artificial Intelligence
(4)
Natural Language Processing
(4)
Core AI · Artificial Intelligence
(4)
Machine Learning
(3)
Resources & Methods
(3)
Computer Vision
(2)
Deep Learning
(2)
Learning Types · Machine Learning
(2)
Interdisciplinary
(1)
Application Areas
(1)
Applications
(1)
Core AI · Computer Vision
(1)
Generation
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Keywords
adversarial attack
(3)
attention mechanism
(1)
text-to-image synthesis
(1)
text-to-image generation
(1)
semantic alignment
(1)
semantic consistency
(1)
diffusion model
(1)
multimodal large language model
(1)
jailbreak attack
(1)
retrieval-augmented generation
(1)
security evaluation
(1)
tool agent
(1)
feature enhancement
(1)
prompt injection
(1)
privacy breach
(1)
error analysis
(1)
input perturbation
(1)
security vulnerability
(1)
llm security
(1)
large language model
(1)
Papers
All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction
ACL 2026
Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems
EMNLP 2025
Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System
ACL 2025
One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems
EMNLP 2025
Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues
ACL 2024
Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement
EMNLP 2024