Seungwon Shin
6 papers · 2022–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Conference Polyglot (3) π Renaissance Researcher (6) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (19) π Cross-Pollinator (14)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π
Keyword Champion
(2)
Conferences
NAACL (4)
ACL (1)
EMNLP (1)
Top co-authors
Keywords
text classification
(2)
domain adaptation
(2)
dark web
(2)
adversarial learning
(2)
backdoor defense
(1)
text analysis
(1)
text representation
(1)
token classification
(1)
document analysis
(1)
backdoor attack
(1)
language model
(1)
parameter-efficient fine-tuning
(1)
domain-specific pretraining
(1)
adversarial input
(1)
masked language modeling
(1)
pretrained language model
(1)
web mining
(1)
linguistic analysis
(1)
byte-pair encoding
(1)
byte pair encoding
(1)
Papers
Improbable Bigrams Expose Vulnerabilities of Incomplete Tokens in Byte-Level Tokenizers
EMNLP 2025
Claim-Guided Textual Backdoor Attack for Practical Applications
NAACL 2025
Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm
NAACL 2025
Ignore Me But Donβt 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