Raze to the Ground: Query-Efficient Adversarial HTML Attacks on Machine-Learning Phishing Webpage Detectors

Machine-learning phishing webpage detectors (ML-PWD) have been shown to suffer from adversarial manipulations of the HTML code of the input webpage. Nevertheless, the attacks recently proposed have demonstrated limited effectiveness due to their lack of optimizing the usage of the adopted manipulations, and they focus solely on specific elements of the HTML code. In this work, we overcome these limitations by first designing a novel set of fine-grained manipulations which allow to modify the HTML code of the input phishing webpage without compromising its maliciousness and visual appearance, i.e., the manipulations are functionality- and rendering-preserving by design. We then select which manipulations should be applied to bypass the target detector by a query-efficient black-box optimization algorithm. Our experiments show that our attacks are able to raze to the ground the performance of current state-of-the-art ML-PWD using just 30 queries, thus overcoming the weaker attacks developed in previous work, and enabling a much fairer robustness evaluation of ML-PWD.

Adversarial ModSecurity: Countering Adversarial SQL Injections with Robust Machine Learning

ModSecurity is widely recognized as the standard open-source Web Application Firewall (WAF), maintained by the OWASP Foundation. It detects malicious requests by matching them against the Core Rule Set, identifying well-known attack patterns. Each rule in the CRS is manually assigned a weight, based on the severity of the corresponding attack, and a request is detected as malicious if the sum of the weights of the firing rules exceeds a given threshold. In this work, we show that this simple strategy is largely ineffective for detecting SQL injection (SQLi) attacks, as it tends to block many legitimate requests, while also being vulnerable to adversarial SQLi attacks, i.e., attacks intentionally manipulated to evade detection. To overcome these issues, we design a robust machine learning model, named AdvModSec, which uses the CRS rules as input features, and it is trained to detect adversarial SQLi attacks. Our experiments show that AdvModSec, being trained on the traffic directed towards the protected web services, achieves a better trade-off between detection and false positive rates, improving the detection rate of the vanilla version of ModSecurity with CRS by 21%. Moreover, our approach is able to improve its adversarial robustness against adversarial SQLi attacks by 42%, thereby taking a step forward towards building more robust and trustworthy WAFs.

Decoding the Secrets of Machine Learning in Malware Classification: A Deep Dive into Datasets, Feature Extraction, and Model Performance

Many studies have proposed machine-learning (ML) models for malware detection and classification, reporting an almost-perfect performance. However, they assemble ground-truth in different ways, use diverse static- and dynamic-analysis techniques for feature extraction, and even differ on what they consider a malware family. As a consequence, our community still lacks an understanding of malware classification results: whether they are tied to the nature and distribution of the collected dataset, to what extent the number of families and samples in the training dataset influence performance, and how well static and dynamic features complement each other. This work sheds light on those open questions. by investigating the key factors influencing ML-based malware detection and classification. For this, we collect the largest balanced malware dataset so far with 67K samples from 670 families (100 samples each), and train state-of-the-art models for malware detection and family classification using our dataset. Our results reveal that static features perform better than dynamic features, and that combining both only provides marginal improvement over static features. We discover no correlation between packing and classification accuracy, and that missing behaviors in dynamically-extracted features highly penalize their performance. We also demonstrate how a larger number of families to classify make the classification harder, while a higher number of samples per family increases accuracy. Finally, we find that models trained on a uniform distribution of samples per family better generalize on unseen data.