Shengwei An
Computer Science · Purdue University West Lafayette
Publications
47
Citations
634
Est. group size
~13
Recurring co-author estimate
Active years
12
Publishing since 2015
Shengwei An's research centers on the security and trustworthiness of machine learning systems, particularly detecting and defending against 'backdoor' attacks—hidden manipulations that cause AI models to behave maliciously under specific triggers. Recent work extends this focus to newer AI systems such as diffusion-based language models and multimodal agents, alongside contributions to privacy-preserving learning and model verification. The publication record also includes some unrelated work in environmental science and educational technology, likely from collaborative or cross-disciplinary projects.
Publication output grew substantially from near zero in 2017-2020 to a peak in 2022, and has remained active with roughly 8 papers per year on average over the last five years.
Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026
- Backdooring Masked Diffusion Language Models
arXiv (Cornell University) · 2026
- Backdooring Masked Diffusion Language Models
arXiv (Cornell University) · 2026
- A Bayesian hierarchical mixture model for extracting process features in a newly developed cloud-based writing platform
Frontiers in Psychology · 2026
- ManimAgent: Self-Evolving Multimodal Agents for Visual Education
arXiv (Cornell University) · 2026
- ManimAgent: Self-Evolving Multimodal Agents for Visual Education
arXiv (Cornell University) · 2026
- CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling
2025
- Inspecting Prediction Confidence for Detecting Black-Box Backdoor Attacks
Proceedings of the AAAI Conference on Artificial Intelligence · 2024
- Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration
2023
- Biochar-supported nZVI for the removal of Cr(VI) from soil and water: Advances in experimental research and engineering applications
Journal of Environmental Management · 2022
- Plastic regulates its co-pyrolysis process with biomass: Influencing factors, model calculations, and mechanisms
Frontiers in Ecology and Evolution · 2022
- An Invisible Black-Box Backdoor Attack Through Frequency Domain
Lecture notes in computer science · 2022
- Confidence Matters: Inspecting Backdoors in Deep Neural Networks via Distribution Transfer
arXiv (Cornell University) · 2022
- Pyrolysis of Biomass and Polypropylene: Influence of Pyrolysis Temperature Range, Biomass Type, and Biomass Polypropylene Mass Ratio on the Synergistic Effect
SSRN Electronic Journal · 2022
- Backdoor Attack through Frequency Domain
arXiv (Cornell University) · 2021
- Augmented example-based synthesis using relational perturbation properties
Proceedings of the ACM on Programming Languages · 2019
- arXiv (Cornell University)×18
- Lecture notes in computer science×2
- 2022 IEEE Symposium on Security and Privacy (SP)×2
- Proceedings of the AAAI Conference on Artificial Intelligence×2
- Journal of Environmental Management×1
- Guangyu Shen
Computer Science · Purdue University West Lafayette
- Guanhong Tao
Computer Science · Indiana University
- Qiuling Xu
Computer Science · Purdue University West Lafayette
- Wenbo Guo
Computer Science · Purdue University West Lafayette
- Qi Alfred Chen
Computer Science · Purdue University West Lafayette
This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.
Last updated Jul 20, 2026.
Claim or correct this profile