Ren Pang
Penn State University
H-index: 6
North America-United States
Top articles of Ren Pang
Defending pre-trained language models as few-shot learners against backdoor attacks
2023/9/23
On the Difficulty of Defending Contrastive Learning against Backdoor Attacks
arXiv preprint arXiv:2312.09057
2023/12/14
Model Extraction Attacks Revisited
arXiv preprint arXiv:2312.05386
2023/12/8
Ren Pang
H-Index: 2
Ting Wang
H-Index: 6
A Change of Heart: Backdoor Attacks on Security-Centric Diffusion Models
2023/10/13
An embarrassingly simple backdoor attack on self-supervised learning
2022/10/13
On the security risks of knowledge graph reasoning
2023/5/3
The Dark Side of AutoML: Towards Architectural Backdoor Search
The 11th International Conference on Learning Representations (ICLR'23)
2022/10/21
Neural Architectural Backdoors
arXiv preprint arXiv:2210.12179
2022/10/21
Reasoning over Multi-view Knowledge Graphs
arXiv preprint arXiv:2209.13702
2022/9/27
Trojanzoo: Towards unified, holistic, and practical evaluation of neural backdoors
2022/6/6
Towards Robust Reasoning over Knowledge Graphs
arXiv preprint arXiv:2110.14693
2021/10/27
On the Security Risks of AutoML
2021/10/12
i-Algebra: towards interactive interpretability of deep neural networks
Proceedings of the AAAI Conference on Artificial Intelligence
2021/5/18
A Tale of Evil Twins: Adversarial Inputs versus Poisoned Models
2020
AdvMind: Inferring Adversary Intent of Black-Box Attacks
2020/8
Co-Authors
