Zhengyu Zhao
20 papers · 2020–2026 · 10 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
π Academic Marathon (5) π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (10) π Cross-Pollinator (12)
π
Cross-Pollinator
(12)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(28)
π
Grand Slam
π€
Dynamic Duo
(10)
π¬
Deep Specialist
(11)
ποΈ
Keyword Collector
(92)
π
Century Club
(19)
β
The Questioner
(3)
β‘
Prolific Year
(8)
Conferences
CVPR (5)
NAACL (3)
AAAI (2)
ICCV (2)
ICML (2)
NIPS (2)
ACL (1)
EMNLP (1)
ICLR (1)
IJCNLP (1)
Top co-authors
Research topics
Keywords
adversarial attack
(5)
adversarial perturbation
(3)
vision transformer
(2)
adversarial example
(2)
adversarial robustness
(2)
vision-language model
(2)
image classification
(2)
large language model
(2)
object detection
(1)
monocular depth estimation
(1)
black-box optimization
(1)
adversarial training
(1)
image compression
(1)
model safety
(1)
autonomous driving
(1)
backdoor attack
(1)
bert model
(1)
activity recognition
(1)
safety alignment
(1)
multimodal learning
(1)
Papers
Privacy on the Fly: A Predictive Adversarial Transformation Network for Mobile Sensor Data
AAAI 2026
Improving Integrated Gradient-based Transferable Adversarial Examples by Refining the Integration Path
AAAI 2025
D3: Training-Free AI-Generated Video Detection Using Second-Order Features
ICCV 2025
Nullu: Mitigating Object Hallucinations in Large Vision-Language Models via HalluSpace Projection
CVPR 2025
Improving Adversarial Transferability on Vision Transformers via Forward Propagation Refinement
CVPR 2025
CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP
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
An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer
NAACL 2025
Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval
ICML 2024
Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving
CVPR 2024
Breaking Semantic Artifacts for Generalized AI-generated Image Detection
NIPS 2024
Composite Backdoor Attacks Against Large Language Models
NAACL 2024
Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?
ICLR 2023
Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression
ICML 2023
What Did You Refer to? Evaluating Co-References in Dialogue
ACL 2021
On Success and Simplicity: A Second Look at Transferable Targeted Attacks
NIPS 2021
What Did You Refer to? Evaluating Co-References in Dialogue
IJCNLP 2021
Profile Consistency Identification for Open-domain Dialogue Agents
EMNLP 2020
Towards Large Yet Imperceptible Adversarial Image Perturbations With Perceptual Color Distance
CVPR 2020