Towards Robustness Certification Against Universal Perturbations

Yi Zeng, Zhouxing Shi, Ming Jin, Feiyang Kang, L. Lyu +2 more
2/12/2026

No official code found. Best implementation: reds-lab/Universal_Pert_Cert (12 stars, MIT, last commit 2023-02-14).

Semantic Scholar

Code Implementations(1)

reds-lab/Universal_Pert_CertCommunity61%
MIT

This repo is the official implementation of the ICLR'23 paper "Towards Robustness Certification Against Universal Perturbations." We calculate the certified robustness against universal perturbations (UAP/ Backdoor) given a trained model.

122Python, Jupyter NotebookFeb 11, 20233 years agoMIT

Cite this paper

@article{zeng2026towards,
  title  = {Towards Robustness Certification Against Universal Perturbations},
  author = {Yi Zeng and Zhouxing Shi and Ming Jin and Feiyang Kang and L. Lyu and Cho-Jui Hsieh and R. Jia},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:d60709222aa772732b9ea644bdb364971c0dea13},
  journal = {ICLR 2023 2023}
}

Discussion