Yuanhe Zhang
7 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 · Bronze
🗺️
Taxonomy Completionist
(17)
Venues
Top co-authors
Research topics
Artificial Intelligence
(7)
Machine Learning
(6)
Core AI
(6)
Learning Types
(4)
Optimization & Theory
(2)
Computer Science
(1)
Mathematics & Optimization
(1)
Speech & Audio
(1)
Analysis
(1)
Application Areas
(1)
Applications
(1)
Bayesian & Probabilistic · Artificial Intelligence
(1)
Bayesian & Probabilistic · Machine Learning
(1)
Probability
(1)
Keywords
resource consumption
(2)
backdoor attack
(2)
adversarial machine learning
(1)
model alignment
(1)
gradient descent
(1)
nonparametric statistics
(1)
linear convergence
(1)
generalization
(1)
multivariate prediction
(1)
adversarial defense
(1)
quasi-bayesian method
(1)
vine copula
(1)
low-rank adaptation
(1)
black-box setting
(1)
predictive distribution
(1)
llm agent
(1)
singular subspace
(1)
security vulnerability
(1)
large audio language model
(1)
denial-of-service attack
(1)
Papers
Hidden in the Noise: Unveiling Backdoors in Audio LLMs Alignment Through Latent Acoustic Pattern Triggers
AAAI 2026
SEE: Signal Embedding Energy for Quantifying Noise Interference in Large Audio Language Models
ACL 2026
Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings
ACL 2025
DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent
EMNLP 2025
LoRA-One: One-Step Full Gradient Could Suffice for Fine-Tuning Large Language Models, Provably and Efficiently
ICML 2025
PD3F: A Pluggable and Dynamic DoS-Defense Framework against resource consumption attacks targeting Large Language Models
EMNLP 2025
Quasi-Bayes meets Vines
NeurIPS 2024