Zhengyu Zhao
20 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 (31) π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π€
Dynamic Duo
(10)
π§¬
Topic Evolution
π
Grand Slam
π¬
Deep Specialist
(12)
β‘
Prolific Year Β· Productive
β
The Questioner
(2)
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(103)
Top co-authors
Research topics
Machine Learning
(14)
Artificial Intelligence
(13)
Core AI Β· Artificial Intelligence
(13)
Learning Types Β· Machine Learning
(12)
Computer Vision
(7)
Deep Learning
(6)
Analysis
(5)
Learning Types Β· Deep Learning
(5)
Application Areas
(4)
Core AI Β· Computer Vision
(3)
Architectures
(2)
Generation
(2)
Models
(2)
Natural Language Processing
(1)
Security & Privacy
(1)
Keywords
adversarial attack
(5)
adversarial perturbation
(4)
adversarial training
(3)
vision-language model
(3)
data poisoning
(2)
large language model
(2)
image classification
(2)
vision transformer
(2)
adversarial example
(2)
adversarial robustness
(2)
black-box optimization
(1)
feature matching
(1)
autonomous driving
(1)
monocular depth estimation
(1)
bert model
(1)
zero-shot learning
(1)
multimodal learning
(1)
model interpretability
(1)
ai-generated content
(1)
model editing
(1)
Papers
PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systems
CVPR 2026
Privacy on the Fly: A Predictive Adversarial Transformation Network for Mobile Sensor Data
AAAI 2026
An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer
NAACL 2025
CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP
CVPR 2025
D3: Training-Free AI-Generated Video Detection Using Second-Order Features
ICCV 2025
Improving Adversarial Transferability on Vision Transformers via Forward Propagation Refinement
CVPR 2025
Improving Integrated Gradient-based Transferable Adversarial Examples by Refining the Integration Path
AAAI 2025
Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection
CVPR 2025
Revisiting Adversarial Patch Defenses on Object Detectors: Unified Evaluation, Large-Scale Dataset, and New Insights
ICCV 2025
Typographic Attacks in a Multi-Image Setting
NAACL 2025
Breaking Semantic Artifacts for Generalized AI-generated Image Detection
NeurIPS 2024
Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval
ICML 2024
Composite Backdoor Attacks Against Large Language Models
NAACL 2024
Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving
CVPR 2024
Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression
ICML 2023
Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?
ICLR 2023
On Success and Simplicity: A Second Look at Transferable Targeted Attacks
NeurIPS 2021
What Did You Refer to? Evaluating Co-References in Dialogue
ACL 2021
Profile Consistency Identification for Open-domain Dialogue Agents
EMNLP 2020
Towards Large Yet Imperceptible Adversarial Image Perturbations With Perceptual Color Distance
CVPR 2020