arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2301.11964cs.LG
收藏

对抗网络和机器学习在文件分类中的应用

Adversarial Networks and Machine Learning for File Classification

United States Naval Academy(美国海军学院)

Ken St. Germain, Josh Angichiodo

摘要:

正确识别正在检查的文件类型是法医调查的关键部分。单独的文件类型表明嵌入的内容,如图片,视频,手稿,电子表格等的情况下,系统所有者可能希望保持他们的文件不可访问或文件类型隐藏,我们建议使用一个对抗训练的机器学习神经网络,以确定文件的真实类型,即使扩展名或文件头被混淆,以复杂的发现。我们的半监督生成对抗网络(SGAN)在对11种不同类型的文件进行分类时,准确率达到97.6%。我们还将我们的网络与传统的独立神经网络和其他三种机器学习算法进行了比较。经过逆向训练的网络被证明是最精确的文件分类器,特别是在监督样本很少的情况下。我们使用SGAN实现的文件分类器在GitHub上实现(https://ksaintg.github.io/SGAN-File-Classier)。

英文摘要:

Correctly identifying the type of file under examination is a critical part of a forensic investigation. The file type alone suggests the embedded content, such as a picture, video, manuscript, spreadsheet, etc. In cases where a system owner might desire to keep their files inaccessible or file type concealed, we propose using an adversarially-trained machine learning neural network to determine a file's true type even if the extension or file header is obfuscated to complicate its discovery. Our semi-supervised generative adversarial network (SGAN) achieved 97.6% accuracy in classifying files across 11 different types. We also compared our network against a traditional standalone neural network and three other machine learning algorithms. The adversarially-trained network proved to be the most precise file classifier especially in scenarios with few supervised samples available. Our implementation of a file classifier using an SGAN is implemented on GitHub (https://ksaintg.github.io/SGAN-File-Classier).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑