A taxonomy and terminology of adversarial machine learning

Tabassi, Elham; Burns, Kevin J.; Hadjimichael, Michael; Molina–Markham, Andrés; Sexton, Julian

doi:10.6028/nist.ir.8269-draft

Cited by 54 publications

(74 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Adversarial attack threat model helps us define the attack and its risk level. Attacks can be categorized based on various parameters like attack timing, attacker knowledge and attacker's goal [36,161].…”

Section: Adversarial Attacks -Disturbance Caused During Malware Detectionmentioning

confidence: 99%

“…As per the NIST Taxonomy for AML, [36] the attacker can aim to disturb during the training phase or the inference phase as given in the Figure 5.…”

Section: Attack Timingmentioning

confidence: 99%

“…Inference time attacks or Exploratory attacks [36,161] which happens during the inference phase to disturb the trained model. It can be classified into Oracle and Evasion attacks.…”

Section: (B) Attacks During Inference Phasementioning

confidence: 99%

“…In evasion attacks [36,180] the attacker crafts adversarial samples by perturbing the input samples which when fed to the trained model causes misclassification. Evasion attacks can be gradient based or gradient free.…”

Section: (Ii) Evasion Attacksmentioning

confidence: 99%

“…DARPA's Guaranteeing AI Robustness against Deception (GARD) [ Cleverhans [30] are few attempts to counter the adversarial attacks on ML models on the image space. The available comprehensive literature review articles on adversarial attacks against ML models and possible defenses in the image space are [31][32][33][34][35][36] to name a few.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Review on Android Malware: Attacks, Countermeasures and Challenges Ahead

Selvaganapathy

Sadasivam

Ravi

2021

JCSANDM

View full text Add to dashboard Cite

Smartphones usage have become ubiquitous in modern life serving as a double-edged sword with opportunities and challenges in it. Along with the benefits, smartphones also have high exposure to malware. Malware has progressively penetrated thereby causing more turbulence. Malware authors have become increasingly sophisticated and are able to evade detection by anti-malware engines. This has led to a constant arms race between malware authors and malware defenders. This survey converges on Android malware and covers a walkthrough of the various obfuscation attacks deployed during malware analysis phase along with the myriad of adversarial attacks operated at malware detection phase. The review also unscrambles the difficulties currently faced in deploying an on-device, lightweight malware detector. It sheds spotlight for researchers to perceive the current state of the art techniques available to fend off malware along with suggestions on possible future directions

show abstract

Section: Adversarial Attacks -Disturbance Caused During Malware Detectionmentioning

confidence: 99%

“…As per the NIST Taxonomy for AML, [36] the attacker can aim to disturb during the training phase or the inference phase as given in the Figure 5.…”

Section: Attack Timingmentioning

confidence: 99%

“…Inference time attacks or Exploratory attacks [36,161] which happens during the inference phase to disturb the trained model. It can be classified into Oracle and Evasion attacks.…”

Section: (B) Attacks During Inference Phasementioning

confidence: 99%

Section: (Ii) Evasion Attacksmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Review on Android Malware: Attacks, Countermeasures and Challenges Ahead

Selvaganapathy

Sadasivam

Ravi

2021

JCSANDM

View full text Add to dashboard Cite

show abstract

Adversarial Machine Learning

Reznik¹

2021

Intelligent Security Systems

View full text Add to dashboard Cite

In this paper (expanded from an invited talk at AISEC 2010), we discuss an emerging field of study: adversarial machine learning-the study of effective machine learning techniques against an adversarial opponent. In this paper, we: give a taxonomy for classifying attacks against online machine learning algorithms; discuss application-specific factors that limit an adversary's capabilities; introduce two models for modeling an adversary's capabilities; explore the limits of an adversary's knowledge about the algorithm, feature space, training, and input data; explore vulnerabilities in machine learning algorithms; discuss countermeasures against attacks; introduce the evasion challenge; and discuss privacy-preserving learning techniques.

show abstract

Explainable deep learning in healthcare: A methodological survey from an attribution view

Jin

Sergeeva

Weng

et al. 2022

WIREs Mechanisms of Disease

View full text Add to dashboard Cite

The increasing availability of large collections of electronic health record (EHR) data and unprecedented technical advances in deep learning (DL) have sparked a surge of research interest in developing DL based clinical decision support systems for diagnosis, prognosis, and treatment. Despite the recognition of the value of deep learning in healthcare, impediments to further adoption in real healthcare settings remain due to the black-box nature of DL. Therefore, there is an emerging need for interpretable DL, which allows end users to evaluate the model decision making to know whether to accept or reject predictions and recommendations before an action is taken. In this review, we focus on the interpretability of the DL models in healthcare. We start by introducing the methods for interpretability in depth and comprehensively as a methodological reference for future researchers or clinical practitioners in this field. Besides the methods' details, we also include a discussion of advantages and disadvantages of these methods and which scenarios each of them is suitable for, so that interested readers can know how to compare and choose among them for use. Moreover, we discuss how these methods, originally developed for solving general-domain problems, have been adapted and applied to healthcare problems and how they can help physicians better understand these data-driven technologies. Overall, we hope this survey can help researchers and practitioners in both artificial intelligence and clinical fields understand what methods we have for enhancing the interpretability of their DL models and choose the optimal one accordingly.

show abstract

A taxonomy and terminology of adversarial machine learning

Cited by 54 publications

References 11 publications

A Review on Android Malware: Attacks, Countermeasures and Challenges Ahead

A Review on Android Malware: Attacks, Countermeasures and Challenges Ahead

Adversarial Machine Learning

Explainable deep learning in healthcare: A methodological survey from an attribution view

Contact Info

Product

Resources

About