Yuekai Huang
7 papers · 2025–2026 · 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 · Silver
🗺️
Taxonomy Completionist
(16)
⭐
Rising Star
(7)
❓
The Questioner
Top co-authors
Research topics
Artificial Intelligence
(6)
Machine Learning
(6)
Core AI · Artificial Intelligence
(6)
Natural Language Processing
(5)
Learning Types
(5)
Resources & Methods
(4)
Application Areas
(2)
Computer Vision
(1)
Interdisciplinary
(1)
Applications
(1)
Core AI · Computer Vision
(1)
Learning Paradigms
(1)
Social
(1)
Keywords
adversarial attack
(3)
retrieval-augmented generation
(2)
large language model
(2)
gradient-based attack
(1)
privacy breach
(1)
error analysis
(1)
input perturbation
(1)
security vulnerability
(1)
tool calling
(1)
model transferability
(1)
llm security
(1)
harmful meme detection
(1)
adversarial injection
(1)
privacy theft
(1)
denial of service
(1)
vulnerability exploitation
(1)
failure analysis
(1)
corpus poisoning
(1)
parameter hallucination
(1)
llm toolchain
(1)
Papers
All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction
ACL 2026
Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in LLMs
EACL 2026
Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems
AAAI 2026
Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systems
EMNLP 2025
From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection
NAACL 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