Dan Ma
3 papers · 2024–2026 · 2 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 · Bronze
Top co-authors
Research topics
Keywords
semantic segmentation
(1)
weakly supervised learning
(1)
prompt engineering
(1)
adversarial training
(1)
deepfake detection
(1)
adversarial attack
(1)
scribble annotation
(1)
proactive forensics
(1)
self-supervised training
(1)
feature modulation
(1)
jailbreak prompt
(1)
large language model
(1)
watermark embedding
(1)
image manipulation localization
(1)
prompt security
(1)
multi-embedding attack
(1)
Papers
Beyond Fully Supervised Pixel Annotations: Scribble-Driven Weakly-Supervised Framework for Image Manipulation Localization
AAAI 2026
Uncovering and Mitigating Destructive Multi-Embedding Attacks in Deepfake Proactive Forensics
AAAI 2026
A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily
NAACL 2024