Zhen Xiang
14 papers · 2005–2026 · 6 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 ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Ultra π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (22)
π§¬
Topic Evolution
π₯
Mega-Team Β· Squad
ποΈ
Keyword Collector
(65)
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
Top co-authors
Research topics
Artificial Intelligence
(12)
Core AI
(12)
Machine Learning
(8)
Learning Types Β· Machine Learning
(6)
Deep Learning
(4)
Learning Types Β· Deep Learning
(4)
Computer Vision
(2)
Security & Privacy
(2)
Analysis
(2)
Application Areas
(2)
Privacy
(2)
Natural Language Processing
(1)
Architectures
(1)
Resources & Methods
(1)
Keywords
backdoor attack
(6)
adversarial attack
(3)
large language model
(3)
llm agent
(3)
adversarial learning
(3)
anomaly detection
(2)
safety evaluation
(2)
neural network
(2)
prompt injection
(2)
adversarial prompt
(2)
chain-of-thought reasoning
(1)
error propagation
(1)
safety alignment
(1)
adversarial robustness
(1)
knowledge base
(1)
model safety
(1)
neural network security
(1)
jailbreak attack
(1)
3d vision
(1)
poisoning attack
(1)
Papers
How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
ACL 2026
IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Review
ACL 2026
GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning
ICML 2025
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
ICLR 2025
SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
ACL 2025
Unveiling Privacy Risks in LLM Agent Memory
ACL 2025
AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
NeurIPS 2024
ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs
ACL 2024
BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
ICLR 2024
Data Free Backdoor Attacks
NeurIPS 2024
UMD: Unsupervised Model Detection for X2X Backdoor Attacks
ICML 2023
Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios
ICLR 2022
A Backdoor Attack Against 3D Point Cloud Classifiers
ICCV 2021
Speed and Sparsity of Regularized Boosting
AISTATS 2005