Zhenhong Zhou
13 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 ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (18) ποΈ Keyword Collector (57)
π
Century Club Β· Bronze
β‘
Prolific Year Β· Productive
π
Renaissance Researcher
(5)
Top co-authors
Research topics
Artificial Intelligence
(13)
Core AI
(13)
Machine Learning
(7)
Learning Types Β· Machine Learning
(4)
Deep Learning
(2)
Natural Language Processing
(2)
Application Areas
(2)
Resources & Methods
(2)
Computer Science
(1)
Reinforcement Learning
(1)
Speech & Audio
(1)
Analysis
(1)
Applications
(1)
Learning Types Β· Deep Learning
(1)
Methods
(1)
Keywords
large language model
(7)
backdoor attack
(3)
safety alignment
(3)
jailbreak attack
(2)
resource consumption
(2)
harmful content
(1)
model safety
(1)
backdoor defense
(1)
hidden state
(1)
black-box setting
(1)
adversarial defense
(1)
language model
(1)
synthetic data
(1)
safety evaluation
(1)
adversarial machine learning
(1)
privacy risk
(1)
model alignment
(1)
attention head
(1)
parameter update
(1)
preference learning
(1)
Papers
Backdoor Collapse: Eliminating Unknown Threats Via Known Backdoor Aggregation In Language Models
ACL 2026
Hidden in the Noise: Unveiling Backdoors in Audio LLMs Alignment Through Latent Acoustic Pattern Triggers
AAAI 2026
RiskLab: A Controlled Toolkit for Probing Emergent Risks in LLM-Based Multi-Agent Systems
ACL 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
On the Role of Attention Heads in Large Language Model Safety
ICLR 2025
PD3F: A Pluggable and Dynamic DoS-Defense Framework against resource consumption attacks targeting Large Language Models
EMNLP 2025
Reinforced Lifelong Editing for Language Models
ICML 2025
Alignment-Enhanced Decoding: Defending Jailbreaks via Token-Level Adaptive Refining of Probability Distributions
EMNLP 2024
Course-Correction: Safety Alignment Using Synthetic Preferences
EMNLP 2024
How Alignment and Jailbreak Work: Explain LLM Safety through Intermediate Hidden States
EMNLP 2024
Quantifying and Analyzing Entity-Level Memorization in Large Language Models
AAAI 2024