Sergey Berezin
4 papers · 2022–2025 · 3 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
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(12)
Venues
Top co-authors
Research topics
Artificial Intelligence
(3)
Machine Learning
(3)
Natural Language Processing
(3)
Core AI
(3)
Learning Types
(3)
Computer Science
(1)
Security & Privacy
(1)
Application Areas
(1)
Applications · Computer Science
(1)
Applications · Natural Language Processing
(1)
Generation
(1)
Privacy
(1)
Resources & Methods
(1)
Understanding
(1)
Keywords
adversarial attack
(3)
large language model
(2)
toxicity detection
(2)
adversarial defense
(1)
adversarial example
(1)
jailbreak attack
(1)
prompt injection
(1)
multilingual model
(1)
abstractive summarization
(1)
moderation system
(1)
obfuscation attack
(1)
neural network
(1)
sentence-level attack
(1)
pretraining objective
(1)
task-in-prompt attack
(1)
jailbreak adversarial attack
(1)
named entity recognition
(1)
ascii art
(1)
text summarization
(1)
safety alignment
(1)
Papers
Evading Toxicity Detection with ASCII-art: A Benchmark of Spatial Attacks on Moderation Systems
ACL 2025
The TIP of the Iceberg: Revealing a Hidden Class of Task-in-Prompt Adversarial Attacks on LLMs
ACL 2025
No offence, Bert - I insult only humans! Multilingual sentence-level attack on toxicity detection networks
EMNLP 2023
Named Entity Inclusion in Abstractive Text Summarization
COLING 2022