Seungwon Shin
7 papers · 2022–2026 · 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Gold 🗺️ Taxonomy Completionist (21) 🐣 Hot Topic Early Bird 🏆 Keyword Champion (2)
🔥
Unstoppable · Bronze
Top co-authors
Research topics
Machine Learning
(6)
Artificial Intelligence
(4)
Natural Language Processing
(4)
Core AI
(4)
Learning Types
(4)
Resources & Methods
(3)
Computer Science
(2)
Application Areas
(2)
Data Science & Analytics
(1)
Deep Learning
(1)
Applications · Natural Language Processing
(1)
Applications · Computer Science
(1)
Generation
(1)
Methods
(1)
Models
(1)
Keywords
dark web
(2)
text classification
(2)
adversarial learning
(2)
domain adaptation
(2)
backdoor attack
(1)
backdoor defense
(1)
model robustness
(1)
traffic analysis
(1)
token classification
(1)
document analysis
(1)
text representation
(1)
language model
(1)
parameter-efficient fine-tuning
(1)
pre-trained language model
(1)
adversarial input
(1)
domain-specific pretraining
(1)
masked language modeling
(1)
service mesh
(1)
text analysis
(1)
natural language processing
(1)
Papers
HybridMesh: A Hardware-software Hybrid Approach for Accelerating Service Mesh Ingress
NSDI 2026
Claim-Guided Textual Backdoor Attack for Practical Applications
NAACL 2025
Improbable Bigrams Expose Vulnerabilities of Incomplete Tokens in Byte-Level Tokenizers
EMNLP 2025
Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm
NAACL 2025
Ignore Me But Don’t Replace Me: Utilizing Non-Linguistic Elements for Pretraining on the Cybersecurity Domain
NAACL 2024
DarkBERT: A Language Model for the Dark Side of the Internet
ACL 2023
Shedding New Light on the Language of the Dark Web
NAACL 2022