Watch, Listen, Understand, Mislead: Tri-modal Adversarial Attacks on Short Videos for Content Appropriateness Evaluation
Paper
•
2507.11968
•
Published
S M Jishanul Islam
smji
AI & ML interests
Computer Vision, NLP, LLMs, Multimodal Deep Learning
Recent Activity
liked
a dataset
6 days ago
itsanmolgupta/mimic-cxr-dataset
upvoted
a
paper
12 days ago
Fast and Accurate Causal Parallel Decoding using Jacobi Forcing
upvoted
a
paper
12 days ago
HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices
Organizations
authored
2
papers
6 months ago