Xinghao Yang
7 papers · 2020–2026 · 4 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 · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(16)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Machine Learning
(6)
Learning Types · Machine Learning
(5)
Artificial Intelligence
(4)
Core AI
(4)
Deep Learning
(3)
Natural Language Processing
(3)
Applications · Natural Language Processing
(3)
Learning Types · Deep Learning
(3)
Optimization & Theory
(3)
Core Methods
(2)
Data Science & Analytics
(1)
Application Areas
(1)
Applications · Data Science & Analytics
(1)
Keywords
text classification
(5)
adversarial attack
(4)
word substitution
(3)
text generation
(2)
model robustness
(1)
natural gradient
(1)
natural language processing
(1)
heuristic search
(1)
information bottleneck
(1)
population mobility
(1)
location estimation
(1)
cross-domain analysis
(1)
feature disentanglement
(1)
mutual information
(1)
semantic similarity
(1)
simulated annealing
(1)
masked language model
(1)
disentangled representation
(1)
adversarial defense
(1)
matrix factorization
(1)
Papers
Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance
ACL 2026
Disentangled Information Bottleneck for Adversarial Text Defense
EMNLP 2025
Adaptive Immune-based Sound-Shape Code Substitution for Adversarial Chinese Text Attacks
EMNLP 2024
Annealing Genetic-based Preposition Substitution for Text Rubbish Example Generation
IJCAI 2023
BESA: BERT-based Simulated Annealing for Adversarial Text Attacks
IJCAI 2021
Bigram and Unigram Based Text Attack via Adaptive Monotonic Heuristic Search
AAAI 2021
Population Location and Movement Estimation through Cross-domain Data Analysis
IJCAI 2020