Chengyu Song
13 papers · 2020–2026 · 9 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (19) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π§¬
Topic Evolution
π
Keyword Champion
(2)
π
Trend Setter
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
β‘
Prolific Year Β· Productive
β
The Questioner
ποΈ
Keyword Collector
(52)
Top co-authors
Research topics
Artificial Intelligence
(8)
Core AI Β· Artificial Intelligence
(8)
Deep Learning
(7)
Computer Vision
(6)
Machine Learning
(6)
Learning Types Β· Machine Learning
(6)
Learning Types Β· Deep Learning
(5)
Analysis
(4)
Models
(2)
Computer Science
(1)
Reinforcement Learning
(1)
Applications
(1)
Architectures
(1)
Core AI Β· Computer Vision
(1)
Core Methods
(1)
Keywords
adversarial attack
(8)
black-box attack
(4)
object detection
(4)
vision-language model
(3)
adversarial perturbation
(2)
generative model
(2)
multi-object scene
(2)
image classification
(2)
transfer attack
(2)
context consistency
(2)
query efficiency
(1)
machine unlearning
(1)
ensemble method
(1)
scene understanding
(1)
embodied agent
(1)
static analysis
(1)
image classifier
(1)
early exit
(1)
surrogate model
(1)
language model
(1)
Papers
A Compilation-Based Under-Constrained Execution Engine
OSDI 2026
HEAL: An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Models
EMNLP 2025
Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models
ICML 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
ADC: Adversarial Attacks Against Object Detection That Evade Context Consistency Checks
WACV 2022
Blackbox Attacks via Surrogate Ensemble Search
NeurIPS 2022
Context-Aware Transfer Attacks for Object Detection
AAAI 2022
GAMA: Generative Adversarial Multi-Object Scene Attacks
NeurIPS 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
NeurIPS 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