SD
S. Dieck
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
2 records found
1
In this paper, we present an L∗-style algorithm for actively learning a bidirectional deterministic finite automaton (biDFA) in polynomial time using three types of oracles. We show how the W-method for the equivalence oracle can be adapted to our algorithm and present a novel heuristic for choosing the orientation of states. With this algorithm, one can identify automata for a subset of the linear languages that includes but is not limited to the regular languages. Since the equivalence oracle is an important part of the algorithm, we also discuss complexity bounds for different versions of the language equivalence problem for biDFAs. These results, together with our algorithm, also prove complexity bounds for the biDFA minimisation problem. Finally, we provide an implementation of the algorithm and experimentally show its performance with different approximation heuristics.
...
In this paper, we present an L∗-style algorithm for actively learning a bidirectional deterministic finite automaton (biDFA) in polynomial time using three types of oracles. We show how the W-method for the equivalence oracle can be adapted to our algorithm and present a novel heuristic for choosing the orientation of states. With this algorithm, one can identify automata for a subset of the linear languages that includes but is not limited to the regular languages. Since the equivalence oracle is an important part of the algorithm, we also discuss complexity bounds for different versions of the language equivalence problem for biDFAs. These results, together with our algorithm, also prove complexity bounds for the biDFA minimisation problem. Finally, we provide an implementation of the algorithm and experimentally show its performance with different approximation heuristics.
SoK
Explainable Machine Learning for Computer Security Applications
Conference paper
(2023)
-
Azqa Nadeem, Daniël Vos, Clinton Cao, Luca Pajola, Simon Dieck, Robert Baumgartner, Sicco Verwer
Explainable Artificial Intelligence (XAI) aims to improve the transparency of machine learning (ML) pipelines. We systematize the increasingly growing (but fragmented) microcosm of studies that develop and utilize XAI methods for defensive and offensive cybersecurity tasks. We identify 3 cybersecurity stakeholders, i.e., model users, designers, and adversaries, who utilize XAI for 4 distinct objectives within an ML pipeline, namely 1) XAI-enabled user assistance, 2) XAI-enabled model verification, 3) explanation verification & robustness, and 4) offensive use of explanations. Our analysis of the literature indicates that many of the XAI applications are designed with little understanding of how they might be integrated into analyst workflows – user studies for explanation evaluation are conducted in only 14% of the cases. The security literature sometimes also fails to disentangle the role of the various stakeholders, e.g., by providing explanations to model users and designers while also exposing them to adversaries. Additionally, the role of model designers is particularly minimized in the security literature. To this end, we present an illustrative tutorial for model designers, demonstrating how XAI can help with model verification. We also discuss scenarios where interpretability by design may be a better alternative. The systematization and the tutorial enable us to challenge several assumptions, and present open problems that can help shape the future of XAI research within cybersecurity.
...
Explainable Artificial Intelligence (XAI) aims to improve the transparency of machine learning (ML) pipelines. We systematize the increasingly growing (but fragmented) microcosm of studies that develop and utilize XAI methods for defensive and offensive cybersecurity tasks. We identify 3 cybersecurity stakeholders, i.e., model users, designers, and adversaries, who utilize XAI for 4 distinct objectives within an ML pipeline, namely 1) XAI-enabled user assistance, 2) XAI-enabled model verification, 3) explanation verification & robustness, and 4) offensive use of explanations. Our analysis of the literature indicates that many of the XAI applications are designed with little understanding of how they might be integrated into analyst workflows – user studies for explanation evaluation are conducted in only 14% of the cases. The security literature sometimes also fails to disentangle the role of the various stakeholders, e.g., by providing explanations to model users and designers while also exposing them to adversaries. Additionally, the role of model designers is particularly minimized in the security literature. To this end, we present an illustrative tutorial for model designers, demonstrating how XAI can help with model verification. We also discuss scenarios where interpretability by design may be a better alternative. The systematization and the tutorial enable us to challenge several assumptions, and present open problems that can help shape the future of XAI research within cybersecurity.