DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness

Authors: Shoumik Saha, Wenxiao Wang, Yigitcan Kaya, Soheil Feizi, Tudor Dumitras

ICLR 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental To our knowledge, we are the first to offer certified robustness in the realm of static detection of malware executables. More surprisingly, through evaluating DRSM against 9 empirical attacks of different types, we observe that the proposed defense is empirically robust to some extent against a diverse set of attacks, some of which even fall out of the scope of its original threat model.
Researcher Affiliation Academia Shoumik Saha, Wenxiao Wang, Yigitcan Kaya, Soheil Feizi & Tudor Dumitras {smksaha, wwx, cankaya, sfeizi, tudor}@umd.edu Department of Computer Science University of Maryland College Park
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks. Figure 7 shows a model architecture diagram, but not pseudocode.
Open Source Code Yes Our code and dataset are available at https://github.com/Shoumik Saha/DRSM
Open Datasets Yes In addition, we collected 15.5K recent benign raw executables from diverse sources, which will be made public as a dataset called PACE (Publicly Accessible Collection(s) of Executables)... Our code and dataset are available at https://github.com/Shoumik Saha/DRSM
Dataset Splits Yes We split our dataset into 70:15:15 ratios for train, validation, and test sets, respectively.
Hardware Specification Yes All the models were re-trained for 10 epochs. We trained the models using multiple gpus at different times. But mostly used gpus were 4 NVIDIA RTX A4000 and 2 RTX A5000.
Software Dependencies No The paper mentions software like the 'secml-malware python library' and 'IDAPro disassembler' but does not provide specific version numbers for any software dependencies.
Experiment Setup Yes For our optimizer, we used Optimizer: SGD learning-rate: 0.01 momentum: 0.9 nesterov: True weight-decay: 1e 3. For training on VTFeed and our dataset, the batch size was 16 and 32, respectively. All the models were re-trained for 10 epochs.