Changjiang Li
12 papers · 2023–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π Cross-Pollinator (14) π Renaissance Researcher (6) π Conference Polyglot (5) πΊοΈ Taxonomy Completionist (14)
π§
Keyword Pioneer
β
The Questioner
Conferences
ACL (3)
ICLR (3)
AAAI (2)
NIPS (2)
EMNLP (1)
ICCV (1)
Top co-authors
Keywords
backdoor attack
(3)
vision-language model
(2)
adversarial learning
(1)
adversarial robustness
(1)
few-shot learning
(1)
neural network security
(1)
self-supervised learning
(1)
humor detection
(1)
adversarial training
(1)
adversarial attack
(1)
diffusion model
(1)
adversarial defense
(1)
text-to-video generation
(1)
jailbreak attack
(1)
privacy protection
(1)
pre-trained language model
(1)
security evaluation
(1)
multimodal reasoning
(1)
concept erasure
(1)
adversarial input
(1)
Papers
ACIArena: Toward Unified Evaluation for Agent Cascading Injection
ACL 2026
βI See What You Did Thereβ: Can Large Vision-Language Models Understand Multimodal Puns?
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
RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
ICLR 2025
AIA: Autoregression-Based Injection Attacks Against Text2SQL Models
AAAI 2025
VideoEraser: Concept Erasure in Text-to-Video Diffusion Models
EMNLP 2025
RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models
ICLR 2025
IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI
NIPS 2023
The Dark Side of AutoML: Towards Architectural Backdoor Search
ICLR 2023
An Embarrassingly Simple Backdoor Attack on Self-supervised Learning
ICCV 2023
Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks
NIPS 2023