Planned maintenance
A system upgrade is planned for 24/9-2024, at 12:00-14:00. During this time DiVA will be unavailable.
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
On the Use of Model-Agnostic Interpretation Methods as Defense Against Adversarial Input Attacks on Tabular Data
Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science.
Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science.
2020 (English)Independent thesis Advanced level (professional degree), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Context. Machine learning is a constantly developing subfield within the artificial intelligence field. The number of domains in which we deploy machine learning models is constantly growing and the systems using these models spread almost unnoticeably in our daily lives through different devices. In previous years, lots of time and effort has been put into increasing the performance of these models, overshadowing the significant risks of attacks targeting the very core of the systems, the trained machine learning models themselves. A specific attack with the aim of fooling the decision-making of a model, called the adversarial input attack, has almost exclusively been researched for models processing image data. However, the threat of adversarial input attacks stretches beyond systems using image data, to e.g the tabular domain which is the most common data domain used in the industry. Methods used for interpreting complex machine learning models can help humans understand the behavior and predictions of these complex machine learning systems. Understanding the behavior of a model is an important component in detecting, understanding and mitigating vulnerabilities of the model.

Objectives. This study aims to reduce the research gap of adversarial input attacks and defenses targeting machine learning models in the tabular data domain. The goal of this study is to analyze how model-agnostic interpretation methods can be used in order to mitigate and detect adversarial input attacks on tabular data.

Methods. The goal is reached by conducting three consecutive experiments where model interpretation methods are analyzed and adversarial input attacks are evaluated as well as visualized in terms of perceptibility. Additionally, a novel method for adversarial input attack detection based on model interpretation is proposed together with a novel way of defensively using feature selection to reduce the attack vector size.

Results. The adversarial input attack detection showed state-of-the-art results with an accuracy over 86%. The proposed feature selection-based mitigation technique was successful in hardening the model from adversarial input attacks by reducing their scores by 33% without decreasing the performance of the model.

Conclusions. This study contributes with satisfactory and useful methods for adversarial input attack detection and mitigation as well as methods for evaluating and visualizing the imperceptibility of attacks on tabular data.

Abstract [sv]

Kontext. Maskininlärning är ett område inom artificiell intelligens som är under konstant utveckling. Mängden domäner som vi sprider maskininlärningsmodeller i växer sig allt större och systemen sprider sig obemärkt nära inpå våra dagliga liv genom olika elektroniska enheter. Genom åren har mycket tid och arbete lagts på att öka dessa modellers prestanda vilket har överskuggat risken för sårbarheter i systemens kärna, den tränade modellen. En relativt ny attack, kallad "adversarial input attack", med målet att lura modellen till felaktiga beslutstaganden har nästan uteslutande forskats på inom bildigenkänning. Men, hotet som adversarial input-attacker utgör sträcker sig utom ramarna för bilddata till andra datadomäner som den tabulära domänen vilken är den vanligaste datadomänen inom industrin. Metoder för att tolka komplexa maskininlärningsmodeller kan hjälpa människor att förstå beteendet hos dessa komplexa maskininlärningssystem samt de beslut som de tar. Att förstå en modells beteende är en viktig komponent för att upptäcka, förstå och mitigera sårbarheter hos modellen.

Syfte. Den här studien försöker reducera det forskningsgap som adversarial input-attacker och motsvarande försvarsmetoder i den tabulära domänen utgör. Målet med denna studie är att analysera hur modelloberoende tolkningsmetoder kan användas för att mitigera och detektera adversarial input-attacker mot tabulär data.

Metod. Det uppsatta målet nås genom tre på varandra följande experiment där modelltolkningsmetoder analyseras, adversarial input-attacker utvärderas och visualiseras samt där en ny metod baserad på modelltolkning föreslås för detektion av adversarial input-attacker tillsammans med en ny mitigeringsteknik där feature selection används defensivt för att minska attackvektorns storlek.

Resultat. Den föreslagna metoden för detektering av adversarial input-attacker visar state-of-the-art-resultat med över 86% träffsäkerhet. Den föreslagna mitigeringstekniken visades framgångsrik i att härda modellen mot adversarial input attacker genom att minska deras attackstyrka med 33% utan att degradera modellens klassifieringsprestanda.

Slutsats. Denna studie bidrar med användbara metoder för detektering och mitigering av adversarial input-attacker såväl som metoder för att utvärdera och visualisera svårt förnimbara attacker mot tabulär data.

Place, publisher, year, edition, pages
2020. , p. 70
Keywords [en]
Machine learning, deep neural networks, model interpretation, cyber security
Keywords [sv]
Maskininlärning, djupa neurala nätverk, modelltolkning, cybersäkerhet
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:bth-20085OAI: oai:DiVA.org:bth-20085DiVA, id: diva2:1450584
External cooperation
Combitech AB
Subject / course
Degree Project in Master of Science in Engineering 30,0 hp
Educational program
DVACD Master of Science in Computer Security
Supervisors
Examiners
Available from: 2020-07-01 Created: 2020-07-01 Last updated: 2022-05-12Bibliographically approved

Open Access in DiVA

fulltext(1778 kB)474 downloads
File information
File name FULLTEXT01.pdfFile size 1778 kBChecksum SHA-512
7b351b55d87bc21bfca121a1bad73f1e407b636b9ea29c55c570fdcb102435efe72707a4ffc0725d4cecda2562000c53e1aef5d21dd2f3394acb34d1f374f470
Type fulltextMimetype application/pdf

By organisation
Department of Computer Science
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 474 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 1519 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf