Search Results for author:
Found 12 papers, 6 papers with code
Distance-Restricted Explanations: Theoretical Underpinnings & Efficient Implementation
Logic-based XAI represents a rigorous approach to explainability; it is model-based and offers the strongest guarantees of rigor of computed explanations.
Adversarial Robustness
Explainable artificial intelligence
+1
Certified Adversarial Robustness of Machine Learning-based Malware Detectors via (De)Randomized Smoothing
As a consequence, the injected content is confined to an integer number of chunks without tampering the other chunks containing the real bytes of the input examples, allowing us to extend our certified robustness guarantees to content insertion attacks.
Adversarial Robustness of Deep Learning-Based Malware Detectors via (De)Randomized Smoothing
Our findings reveal that the chunk-based smoothing classifiers exhibit greater resilience against adversarial malware examples generated with state-of-the-art evasion attacks, outperforming a non-smoothed classifier and a randomized smoothing-based classifier by a great margin.
A Robust Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via (De)Randomized Smoothing
Our findings reveal that the chunk-based smoothing classifiers exhibit greater resilience against adversarial malware examples generated with state-of-the-are evasion attacks, outperforming a non-smoothed classifier and a randomized smoothing-based classifier by a great margin.
On Logic-Based Explainability with Partially Specified Inputs
The paper shows that most of the algorithms proposed in recent years for computing logic-based explanations can be generalized for computing explanations given the partially specified inputs.
Feature Necessity & Relevancy in ML Classifier Explanations
Given a machine learning (ML) model and a prediction, explanations can be defined as sets of features which are sufficient for the prediction.
Orthrus: A Bimodal Learning Architecture for Malware Classification
Malware detection and classification is a challenging problem and an active area of research.
HYDRA: A multimodal deep learning framework for malware classification
While traditional machine learning methods for malware detection largely depend on hand-designed features, which are based on experts’ knowledge of the domain, end-to-end learning approaches take the raw executable as input, and try to learn a set of descriptive features from it.
A Hierarchical Convolutional Neural Network for Malware Classification
Novel approaches in the literature treat an executable as a sequence of bytes or as a sequence of assembly language instructions.
An End-to-End Deep Learning Architecture for Classification of Malware’s Binary Content
In traditional machine learning techniques for malware detection and classification, significant efforts are expended on manually designing features based on expertise and domain-specific knowledge.
Classification of Malware by Using Structural Entropy on Convolutional Neural Networks
Motivated by the visual similarity between streams of entropy of malicious software belonging to the same family, we propose a file agnostic deep learning approach for categorization of malware.
Ranked #5 on
Malware Classification
on Microsoft Malware Classification Challenge
(LogLoss metric)
Convolutional Neural Network for Classification of Malware Assembly Code
Traditional signature-based methods have started becoming inadequnate to deal with next generation malware which utilize sophisticated obfuscation (polymorphic and metamorphic) techniques to evade detection.
