Securebert Plus

🚀 SecureBERT+

SecureBERT+ is an enhanced version of the SecureBERT model. It is trained on a corpus eight times larger than its predecessor, using 8xA100 GPUs. This version shows an average 9% improvement in the Masked Language Model (MLM) task, significantly advancing language understanding and representation learning in the cybersecurity domain.

SecureBERT is a domain - specific language model based on RoBERTa. It is trained on a large amount of cybersecurity data and fine - tuned to understand and represent cybersecurity textual data.

📚 Documentation

Dataset

Load Model

SecureBERT+ has been uploaded to the Huggingface framework.

from transformers import RobertaTokenizer, RobertaModel
import torch

tokenizer = RobertaTokenizer.from_pretrained("ehsanaghaei/SecureBERT_Plus")
model = RobertaModel.from_pretrained("ehsanaghaei/SecureBERT_Plus")

inputs = tokenizer("This is SecureBERT Plus!", return_tensors="pt")
outputs = model(**inputs)

last_hidden_states = outputs.last_hidden_state

Fill Mask (MLM)

Use the following code to predict the masked word in the given sentences:

#!pip install transformers
#!pip install torch
#!pip install tokenizers

import torch
import transformers
from transformers import RobertaTokenizer, RobertaTokenizerFast

tokenizer = RobertaTokenizerFast.from_pretrained("ehsanaghaei/SecureBERT_Plus")
model = transformers.RobertaForMaskedLM.from_pretrained("ehsanaghaei/SecureBERT_Plus")

def predict_mask(sent, tokenizer, model, topk =10, print_results = True):
    token_ids = tokenizer.encode(sent, return_tensors='pt')
    masked_position = (token_ids.squeeze() == tokenizer.mask_token_id).nonzero()
    masked_pos = [mask.item() for mask in masked_position]
    words = []
    with torch.no_grad():
        output = model(token_ids)

    last_hidden_state = output[0].squeeze()

    list_of_list = []
    for index, mask_index in enumerate(masked_pos):
        mask_hidden_state = last_hidden_state[mask_index]
        idx = torch.topk(mask_hidden_state, k=topk, dim=0)[1]
        words = [tokenizer.decode(i.item()).strip() for i in idx]
        words = [w.replace(' ','') for w in words]
        list_of_list.append(words)
        if print_results:
            print("Mask ", "Predictions: ", words)

    best_guess = ""
    for j in list_of_list:
        best_guess = best_guess + "," + j[0]

    return words


while True:
    sent = input("Text here: \t")
    print("SecureBERT: ")
    predict_mask(sent, tokenizer, model)
     
    print("===========================\n")

Other model variants

• SecureGPT
• SecureDeBERTa
• SecureBERT

📄 License

The model is licensed under cc - by - nc - 4.0.

📋 Widget Examples

Native API functions

Native API functions such as , may be directed invoked via system calls/syscalls, but these features are also often exposed to user - mode applications via interfaces and libraries.

Assigning the PPID of a new process

One way of explicitly assigning the PPID of a new process is via the API call, which supports a parameter that defines the PPID to use.

Enable Safe DLL Search Mode

Enable Safe DLL Search Mode to force search for system DLLs in directories with greater restrictions (e.g. %%) to be used before local directory DLLs (e.g. a user's home directory)

GuLoader is a file downloader

GuLoader is a file downloader that has been used since at least December 2019 to distribute a variety of , including NETWIRE, Agent Tesla, NanoCore, and FormBook.

📖 Reference

@inproceedings{aghaei2023securebert, title={SecureBERT: A Domain - Specific Language Model for Cybersecurity}, author={Aghaei, Ehsan and Niu, Xi and Shadid, Waseem and Al - Shaer, Ehab}, booktitle={Security and Privacy in Communication Networks: 18th EAI International Conference, SecureComm 2022, Virtual Event, October 2022, Proceedings}, pages={39--56}, year={2023}, organization={Springer} }