Adversarial Examples for Malware Detection

By Kathrin Grosse, Nicolas Papernot, Praveen Manoharan, Michael Backes, Patrick Drew McDaniel. 2017

589 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Software, Safety, Robustness & Interpretability, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Software

In Safety, Robustness & Interpretability

In Signal Processing

Citations in the corpus

You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion (2020, background): “Prior research on the security of neural code models focused on code summarization and classification (especially for malware analysis [24, 44]), only in the setting where the attacker can modify inputs into the model at inference time.”
Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning (2017, background): “Even in the domain of malware detection, adversarial examples seem to be a novel threat [10], while the vulnerability of learning-based malware detectors to evasion is clearly a consolidated issue [36, 37, 46].”
Adversarial Training and Robustness for Multiple Perturbations (2019, background): “, virtual assistants [5], malware detectors [16] or ad-blockers [39]).”
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey (2018, background): “Further examples of successful adversarial attacks against deep lrearning based malware classification can also be found in [64], [107], and [124].”
Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey (2019, methodology): “[45] (and [46]) is the first work to attack neural malware detector.”
Intriguing Properties of Adversarial ML Attacks in the Problem Space (2019, background): “The most related approaches to our novel attack are on attribution [58], and on adversarial malware generation [31, 60, 75].”
Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks (2018, background): “This may be done against systems leveraging static code analysis, by injecting instructions that will never be executed [11, 15, 45].”
TESSERACT: Eliminating Experimental Bias in Malware Classification across Space and Time (2018, methodology): “ impact of experimental bias (§3), we propose speciﬁc constraints and metrics to allow fair and unbiased comparisons (§4). Since ALG1 and ALG2 adopt traditional ML algorithms, in§4we also consider DL [22], a deep learning-based approach that takes as input the same features as ALG1 [4]. We include D”
Adversarial Attacks on Node Embeddings via Graph Poisoning (2018, background): “While most works focus on image classification, recent works also study adversarial examples in other domains (Grosse et al., 2017; Liang et al., 2018).”
Exploring Backdoor Poisoning Attacks Against Malware Classifiers (2020, background): “The former class has been extensively explored in the context of computer vision [16], and previous research efforts in this direction have also investigated the applicability of such techniques to malware classification [11, 25, 30, 46, 55].”
Fast and Stable Interval Bounds Propagation for Training Verifiably Robust Models (2019, unknown): “Deep learning models achieve impressive performance in computer vision Krizhevsky et al. [2012], natural language processing Hinton et al.”
A Survey of Android Malware Detection with Deep Neural Models (2020, methodology): “A four-layered FCN was proposed in Reference [76] for detecting Android malware.”
Review of Artificial Intelligence Adversarial Attack and Defense Technologies (2019, background): “In articles [78,79], successful cases of adversarial attacks against the malware classification based on deep learning are proposed.”
Real-Time Adversarial Attacks (2019, background): “…classiﬁcation, and malware detection, where they have also been shown to be highly effective [Moosavi-Dezfooli et al. , 2016; Cisse et al. , 2017; Gong and Poellabauer, 2017; Alzantot et al. , 2018; Carlini and Wagner, 2018; Sch¨onherr et al. , 2018; Ebrahimi et al. , 2017; Grosse et al. , 2017].”
Android HIV: A Study of Repackaging Malware for Evading Machine-Learning Detection (2018, methodology): “, [8], [16]) that simply apply perturbations in AndroidManifest.”
Identify Susceptible Locations in Medical Records via Adversarial Attacks on Deep Predictive Models (2018, methodology): “[16] generated adversarial examples by leveraging algorithms of DNN attacks.”