Zidi Xiong
9 papers · 2023–2026 · 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
(15)
👥
Mega-Team · Squad
Venues
Top co-authors
Research topics
Keywords
backdoor attack
(3)
large language model
(2)
adversarial robustness
(2)
conformal prediction
(1)
adversarial machine learning
(1)
toxicity detection
(1)
anomaly detection
(1)
error propagation
(1)
certified defense
(1)
adversarial attack
(1)
jailbreaking attack
(1)
safety evaluation
(1)
chain-of-thought prompting
(1)
multilingual reasoning
(1)
prompt injection
(1)
experience replay
(1)
clustering approach
(1)
memory management
(1)
minimax optimization
(1)
probabilistic modeling
(1)
Papers
How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
ACL 2026
GuardAgent: Safeguard LLM Agents via Knowledge-Enabled Reasoning
ICML 2025
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models
ICLR 2025
When Models Reason in Your Language: Controlling Thinking Language Comes at the Cost of Accuracy
EMNLP 2025
BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
ICLR 2024
RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content
ICML 2024
CBD: A Certified Backdoor Detector Based on Local Dominant Probability
NeurIPS 2023
DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
NeurIPS 2023
UMD: Unsupervised Model Detection for X2X Backdoor Attacks
ICML 2023