Chengyu Song
12 papers · 2020–2025 · 8 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (15) π Conference Polyglot (8) π Academic Marathon (5) π§ Keyword Pioneer
π
Conference Polyglot
(8)
π
Keyword Champion
(2)
π₯
Unstoppable
(6)
β‘
Prolific Year
(5)
π
Century Club
(12)
β
The Questioner
Conferences
NIPS (3)
EMNLP (2)
WACV (2)
AAAI (1)
CVPR (1)
ECCV (1)
ICCV (1)
ICML (1)
Top co-authors
Keywords
adversarial attack
(8)
object detection
(4)
black-box attack
(3)
adversarial perturbation
(2)
transfer attack
(2)
vision-language model
(2)
multi-object scene
(2)
context consistency
(2)
image classification
(2)
generative model
(2)
query efficiency
(1)
ensemble method
(1)
language model
(1)
surrogate model
(1)
machine unlearning
(1)
scene understanding
(1)
hallucination rate
(1)
adversarial example
(1)
embodied agent
(1)
image classifier
(1)
Papers
Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models
ICML 2025
HEAL: An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Models
EMNLP 2025
Can Textual Unlearning Solve Cross-Modality Safety Alignment?
EMNLP 2024
Leveraging Local Patch Differences in Multi-Object Scenes for Generative Adversarial Attacks
WACV 2023
Blackbox Attacks via Surrogate Ensemble Search
NIPS 2022
ADC: Adversarial Attacks Against Object Detection That Evade Context Consistency Checks
WACV 2022
Context-Aware Transfer Attacks for Object Detection
AAAI 2022
GAMA: Generative Adversarial Multi-Object Scene Attacks
NIPS 2022
Zero-Query Transfer Attacks on Context-Aware Object Detectors
CVPR 2022
Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations
NIPS 2021
Exploiting Multi-Object Relationships for Detecting Adversarial Attacks in Complex Scenes
ICCV 2021
Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency
ECCV 2020