Input-Specific Robustness Certification for Randomized Smoothing

Authors: Ruoxin Chen, Jie Li, Junchi Yan, Ping Li, Bin Sheng6295-6303

AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The empirical results on CIFAR-10 and Image Net show that ISS can speed up the certification by more than three times at a limited cost of 0.05 certified radius. Meanwhile, ISS surpasses IAS on the average certified radius across the extensive hyperparameter settings.
Researcher Affiliation Academia 1 Shanghai Jiao Tong University 2 The Hong Kong Polytechnic University {chenruoxin, lijiecs, yanjunchi}@sjtu.edu.cn, p.li@polyu.edu.hk, shengbin@cs.sjtu.edu.cn
Pseudocode Yes Algorithm 1: Compute ISS mapping ψISS( )
Open Source Code Yes We release our code in https: //github.com/roy-ch/Input-Specific-Certification.
Open Datasets Yes We evaluate our proposed method ISS on two benchmark datasets: CIFAR-10 (Krizhevsky 2009) and Image Net (Russakovsky et al. 2015).
Dataset Splits No The paper mentions using test data but does not explicitly provide specific training, validation, and test dataset splits with percentages or sample counts for reproduction.
Hardware Specification Yes All the experiments are conducted on CPU (16 Intel(R) Xeon(R) Gold 5222 CPU @ 3.80GHz) and GPU (one NVIDIA RTX 2080 Ti).
Software Dependencies No The paper does not specify software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes The hyperparameters are listed in Table 2.