Attacks on Visualization-Based Malware Detection: Balancing Effectiveness and Executability

Benkraouda, Hadjer; Qian, Jingyu; Tran, Hung Quoc; Kaplan, Berkay

doi:10.1007/978-3-030-87839-9_5

Cited by 1 publication

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Benkraouda et al [20] proposes a framework that mixes a mask generator to highlight the bytes that are possible to manipulate while retaining executability, adversarial example generation using a Carlini-Wagner (CW) attack [47] and an optimization step that iteratively modifies the masked bytes by comparing the generated adversarial data to a set of known instructions. It fits the "Content Manipulation" category illustrated in Figure 2.…”

Section: Malware Injectionmentioning

confidence: 99%

“…Regarding the data used to evaluate the attacks, most of the works listed here used some sort of private dataset either by collecting samples from malware hosting services or expanding public ones-Benkraouda et al [20] merged malimg [11] and benign samples from the Architecture Object Code Dataset (AOCD) [49], while Khormali et al [19] used BIG 2015 [31] and also formed a private IoT dataset. A summary of the functionalitypreserving attacks can be found in Table 2.…”

Section: Malware Injectionmentioning

confidence: 99%

“…Benkraouda et al [20] Adversarial Generation + Optimization CNN [19,51] Private (combination of malimg [11] and AOCD [49])…”

Section: Malware Injectionmentioning

confidence: 99%

“…The classification approaches evaluated in this work are based on methods that learn straight from the raw bytes of the file, ranging from methodologies that reinterpret the sample as a grayscale image up to preprocessing each sample as a 1D vector in their execution [9,[11][12][13][14][15][16][17][18][19][20]. We want to evaluate the vulnerability of these variants to the already known adversarial examples [21], which is an approach with increasing popularity in the literature, especially in the context of malware [10,12,19,20,[22][23][24][25]. There are some limitations that must be observed, though, since the perturbations added to malware samples must be drawn from a discrete domain.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

On Deceiving Malware Classification with Section Injection

Silva

Segundo

2023

MAKE

View full text Add to dashboard Cite

We investigate how to modify executable files to deceive malware classification systems. This work’s main contribution is a methodology to inject bytes across a malware file randomly and use it both as an attack to decrease classification accuracy but also as a defensive method, augmenting the data available for training. It respects the operating system file format to make sure the malware will still execute after our injection and will not change its behavior. We reproduced five state-of-the-art malware classification approaches to evaluate our injection scheme: one based on Global Image Descriptor (GIST) + K-Nearest-Neighbors (KNN), three Convolutional Neural Network (CNN) variations and one Gated CNN. We performed our experiments on a public dataset with 9339 malware samples from 25 different families. Our results show that a mere increase of 7% in the malware size causes an accuracy drop between 25% and 40% for malware family classification. They show that an automatic malware classification system may not be as trustworthy as initially reported in the literature. We also evaluate using modified malware alongside the original ones to increase networks robustness against the mentioned attacks. The results show that a combination of reordering malware sections and injecting random data can improve the overall performance of the classification. All the code is publicly available.

show abstract

Section: Malware Injectionmentioning

confidence: 99%