Zhibo Jin
~Zhibo_Jin1
12
论文总数
6.0
年均投稿
平均评分
接收情况4/12
会议分布
ICLR
11
ICML
1
发表论文 (12 篇)
20259 篇
4
Rethinking Lipschitzness Data-free Backdoor Defense
ICLR 2025Rejected
4
Unbiased Attribution with Intrinsic Information
ICLR 2025Rejected
4
Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability
ICLR 2025Poster
4
Splitting & Integrating: Out-of-Distribution Detection via Adversarial Gradient Attribution
ICML 2025Poster
4
Splitting & Integrating: Out-of-Distribution Detection via Adversarial Gradient Attribution
ICLR 2025Rejected
4
K&L: Penetrating Backdoor Defense with Key and Locks
ICLR 2025Rejected
3
Feature Level Instance Attribution
ICLR 2025Rejected
4
SSLA: A Generalized Attribution Method for Interpreting Self-Supervised Learning without Downstream Task Dependency
ICLR 2025Rejected
4
PAR-AdvGAN: Improving Adversarial Attack Capability with Progressive Auto-Regression AdvGAN
ICLR 2025Rejected
20243 篇
3
Enhancing Transferable Adversarial Attacks on Vision Transformers through Gradient Normalization Scaling and High-Frequency Adaptation
ICLR 2024Poster
4
Iterative Search Attribution for Deep Neural Networks
ICLR 2024withdrawn
4
AttEXplore: Attribution for Explanation with model parameters eXploration
ICLR 2024Poster