Dan Ma
3 papers · 2024–2026 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
π
Conference Polyglot
(2)
π
Interdisciplinary Bridge
π§
Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
AAAI (2)
NAACL (1)
Top co-authors
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
Uncovering and Mitigating Destructive Multi-Embedding Attacks in Deepfake Proactive Forensics
AAAI 2026
Beyond Fully Supervised Pixel Annotations: Scribble-Driven Weakly-Supervised Framework for Image Manipulation Localization
AAAI 2026
A Wolf in Sheepβs Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily
NAACL 2024