Zikui Cai
10 papers · 2020–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (21) π§ Keyword Pioneer π Cross-Pollinator (15) π Academic Marathon (5) π Conference Polyglot (7)
π
Interdisciplinary Bridge
π₯
Unstoppable
(6)
π
Century Club
(10)
β
The Questioner
Conferences
AAAI (2)
CVPR (2)
ICCV (2)
ECCV (1)
EMNLP (1)
ICML (1)
NIPS (1)
Top co-authors
Keywords
adversarial attack
(5)
object detection
(4)
blackbox attack
(2)
ensemble method
(2)
transfer attack
(2)
ensemble learning
(2)
black-box attack
(2)
safety alignment
(1)
transfer learning
(1)
semantic segmentation
(1)
query efficiency
(1)
feature disentanglement
(1)
machine unlearning
(1)
privacy preservation
(1)
adversarial robustness
(1)
language model
(1)
adversarial perturbation
(1)
knowledge distillation
(1)
surrogate model
(1)
adversarial learning
(1)
Papers
Targeted Unlearning with Single Layer Unlearning Gradient
ICML 2025
Zero-Shot Vision Encoder Grafting via LLM Surrogates
ICCV 2025
Can Textual Unlearning Solve Cross-Modality Safety Alignment?
EMNLP 2024
Disguise without Disruption: Utility-Preserving Face De-identification
AAAI 2024
Ensemble-Based Blackbox Attacks on Dense Prediction
CVPR 2023
Blackbox Attacks via Surrogate Ensemble Search
NIPS 2022
Context-Aware Transfer Attacks for Object Detection
AAAI 2022
Zero-Query Transfer Attacks on Context-Aware Object Detectors
CVPR 2022
Exploiting Multi-Object Relationships for Detecting Adversarial Attacks in Complex Scenes
ICCV 2021
Solving Phase Retrieval with a Learned Reference
ECCV 2020