Intra-section code cave injection for adversarial evasion attacks on windows PE malware file

Windows malware is predominantly available in cyberspace and is a prime target for deliberate adversarial evasion attacks. Although researchers have investigated the adversarial malware attack problem, a multitude of important questions remain unanswered, including (a) Are the existing techniques to inject adversarial perturbations in Windows Portable Executable (PE) malware files effective enough for evasion purposes?; (b) Does the attack process preserve the original behavior of malware?; (c) Are there unexplored approaches/locations that can be used to carry out adversarial evasion attacks on Windows PE malware?; and (d) What are the optimal locations and sizes of adversarial perturbations required to evade an ML-based malware detector without significant structural change in the PE file? To answer some of these questions, this work proposes a novel approach that injects a code cave within the section (i.e., intra-section) of Windows PE malware files to make space for adversarial perturbations. Additionally, a code loader is injected into the PE file, which reverses the effects of adversarial malware during execution, preserving the malware’s functionality and executability. To understand the effectiveness of our approach, we inject adversarial perturbations inside the .text, .data and .rdata sections, generated using the gradient descent and Fast Gradient Sign Method (FGSM) to target the two popular CNN-based malware detectors, MalConv and MalConv2. Our experimental analysis yielded impressive results, achieving an evasion rate of 92.31% with gradient descent and 96.26% with FGSM when targeting MalConv, as compared to the evasion rate of 16.17% for append attacks. Similarly, in the case of an attack against MalConv2, our approach achieves a remarkable maximum evasion rate of 97.93% with gradient descent and 94.34% with FGSM, significantly surpassing the 4.01% and 54.75% evasion rates observed with append attacks.