Seungju Cho
6 papers · 2022–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(3)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(10)
π§
Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
CVPR (2)
ICLR (2)
AAAI (1)
ACL (1)
Top co-authors
Keywords
transferable attack
(2)
targeted adversarial attack
(2)
adversarial example
(2)
adversarial training
(1)
safety alignment
(1)
feature space
(1)
3d object
(1)
refusal behavior
(1)
class incremental learning
(1)
flat loss landscape
(1)
jailbreak detection
(1)
targeted attack
(1)
class incremental
(1)
input diversity
(1)
feature mixup
(1)
financial language model
(1)
clean feature mixup
(1)
continual learning
(1)
flatness preserving
(1)
adversarial robustness
(1)
Papers
FinHarmBench: Financial Jailbreak Benchmark and Unsupervised Safety Fine-Tuning via Refusal Steering Distillation
ACL 2026
Enhancing Robustness in Incremental Learning with Adversarial Training
AAAI 2025
Long-tailed Adversarial Training with Self-Distillation
ICLR 2025
Indirect Gradient Matching for Adversarial Robust Distillation
ICLR 2025
Introducing Competition To Boost the Transferability of Targeted Adversarial Examples Through Clean Feature Mixup
CVPR 2023
Improving the Transferability of Targeted Adversarial Examples Through Object-Based Diverse Input
CVPR 2022