Changjiang Li
12 papers · 2023–2026 · 6 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 ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(23)
💎
Century Club · Bronze
❓
The Questioner
(2)
Top co-authors
Research topics
Artificial Intelligence
(10)
Core AI
(10)
Deep Learning
(5)
Machine Learning
(5)
Natural Language Processing
(3)
Learning Types · Machine Learning
(3)
Models
(3)
Application Areas
(2)
Learning Types · Deep Learning
(2)
Computer Science
(1)
Computer Vision
(1)
Applications · Natural Language Processing
(1)
Applications · Computer Science
(1)
Generation
(1)
Learning Paradigms
(1)
Keywords
backdoor attack
(4)
diffusion model
(3)
vision-language model
(2)
adversarial attack
(2)
image generation
(2)
adversarial robustness
(2)
jailbreak attack
(2)
generative model
(1)
few-shot learning
(1)
benchmark evaluation
(1)
adversarial training
(1)
neural architecture search
(1)
text-to-video generation
(1)
humor detection
(1)
language model
(1)
self-supervised learning
(1)
adversarial defense
(1)
neural network security
(1)
adversarial learning
(1)
representation learning
(1)
Papers
ACIArena: Toward Unified Evaluation for Agent Cascading Injection
ACL 2026
Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content?
AAAI 2026
Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors
ACL 2026
“I See What You Did There”: Can Large Vision-Language Models Understand Multimodal Puns?
ACL 2026
AIA: Autoregression-Based Injection Attacks Against Text2SQL Models
AAAI 2025
RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models
ICLR 2025
RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
ICLR 2025
VideoEraser: Concept Erasure in Text-to-Video Diffusion Models
EMNLP 2025
An Embarrassingly Simple Backdoor Attack on Self-supervised Learning
ICCV 2023
Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks
NeurIPS 2023
IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI
NeurIPS 2023
The Dark Side of AutoML: Towards Architectural Backdoor Search
ICLR 2023