Hanxi Guo
6 papers · 2024–2026 · 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(16)
Top co-authors
Research topics
Artificial Intelligence
(5)
Core AI
(5)
Machine Learning
(4)
Deep Learning
(3)
Application Areas
(3)
Learning Types · Machine Learning
(3)
Natural Language Processing
(1)
Security & Privacy
(1)
Applications
(1)
Learning Paradigms
(1)
Learning Types · Deep Learning
(1)
Models
(1)
Privacy
(1)
Techniques
(1)
Keywords
adversarial attack
(2)
ai-generated text detection
(2)
adversarial learning
(1)
text classification
(1)
backdoor attack
(1)
diffusion model
(1)
surrogate model
(1)
safety evaluation
(1)
watermark detection
(1)
jailbreak attack
(1)
cross-entropy loss
(1)
context inference
(1)
model poisoning
(1)
black-box detection
(1)
safety benchmark
(1)
logit analysis
(1)
ai-generated text
(1)
large language model
(1)
neural network
(1)
origin detection
(1)
Papers
Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening
WACV 2026
Poisoning with a Pill: Circumventing Detection in Federated Learning
AAAI 2026
JailbreakDiffBench: A Comprehensive Benchmark for Jailbreaking Diffusion Models
ICCV 2025
Profiler: Black-box AI-generated Text Origin Detection via Context-aware Inference Pattern Analysis
EMNLP 2025
BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens
NeurIPS 2024
UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening
ECCV 2024