Nael Abu-Ghazaleh
5 papers · 2023–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (5) π Renaissance Researcher (5) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (11) π§ Keyword Pioneer
π
Cross-Pollinator
(14)
Conferences
ACL (1)
CVPR (1)
EMNLP (1)
ICLR (1)
WACV (1)
Top co-authors
Keywords
adversarial attack
(3)
safety alignment
(2)
object detection
(2)
adversarial patch
(2)
multimodal learning
(1)
jailbreak attack
(1)
multimodal language model
(1)
defense mechanism
(1)
llm safety
(1)
entropy analysis
(1)
image recovery
(1)
deformable transformer
(1)
attention manipulation
(1)
large language model
(1)
patch localization
(1)
adversarial learning
(1)
deformable vision transformer
(1)
vision transformer
(1)
computer vision
(1)
attention mechanism
(1)
Papers
Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment
EMNLP 2025
Adversarial Attention Deficit: Fooling Deformable Vision Transformers with Collaborative Adversarial Patches
WACV 2025
Vulnerabilities of Large Language Models to Adversarial Attacks
ACL 2024
Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models
ICLR 2024
Jedi: Entropy-Based Localization and Removal of Adversarial Patches
CVPR 2023