English
Related papers

Related papers: Can We Trust Your Explanations? Sanity Checks for …

200 papers

When machine learning is used for Android malware detection, an app needs to be represented in a numerical format for training and testing. We identify a widespread occurrence of distinct Android apps that have identical or nearly identical…

Cryptography and Security · Computer Science 2025-07-31 Guojun Liu , Doina Caragea , Xinming Ou , Sankardas Roy

Large Language Models (LLMs) offer natural language explanations as an alternative to feature attribution methods for model interpretability. However, despite their plausibility, they may not reflect the model's true reasoning faithfully.…

Computation and Language · Computer Science 2025-12-29 Kerem Zaman , Shashank Srivastava

Methods for interpreting machine learning black-box models increase the outcomes' transparency and in turn generates insight into the reliability and fairness of the algorithms. However, the interpretations themselves could contain…

Machine Learning · Computer Science 2019-06-05 Yujia Zhang , Kuangyan Song , Yiming Sun , Sarah Tan , Madeleine Udell

Explanation methods have emerged as an important tool to highlight the features responsible for the predictions of neural networks. There is mounting evidence that many explanation methods are rather unreliable and susceptible to malicious…

Computation and Language · Computer Science 2022-06-27 Shriya Atmakuri , Tejas Chheda , Dinesh Kandula , Nishant Yadav , Taesung Lee , Hessel Tuinhof

While the evaluation of explanations is an important step towards trustworthy models, it needs to be done carefully, and the employed metrics need to be well-understood. Specifically model randomization testing is often overestimated and…

Recent years have seen a boom in interest in machine learning systems that can provide a human-understandable rationale for their predictions or decisions. However, exactly what kinds of explanation are truly human-interpretable remains…

Artificial Intelligence · Computer Science 2018-02-05 Menaka Narayanan , Emily Chen , Jeffrey He , Been Kim , Sam Gershman , Finale Doshi-Velez

Due to its open-source nature, Android operating system has been the main target of attackers to exploit. Malware creators always perform different code obfuscations on their apps to hide malicious activities. Features extracted from these…

Cryptography and Security · Computer Science 2022-11-02 Yueming Wu , Shihan Dou , Deqing Zou , Wei Yang , Weizhong Qiang , Hai Jin

It is well-known that Android malware constantly evolves so as to evade detection. This causes the entire malware population to be non-stationary. Contrary to this fact, most of the prior works on Machine Learning based Android malware…

Cryptography and Security · Computer Science 2017-07-07 Annamalai Narayanan , Mahinthan Chandramohan , Lihui Chen , Yang Liu

Android malware detection continues to face persistent challenges stemming from long-term concept drift and class imbalance, as evolving malicious behaviors and shifting usage patterns dynamically reshape feature distributions. Although…

Computational Engineering, Finance, and Science · Computer Science 2025-09-10 Yi Xie , Ziyuan Yang , Yongqiang Huang , Yinyu Chen , Lei Zhang , Liang Liu , Yi Zhang

The Android operating system has become the most popular operating system for smartphones and tablets leading to a rapid rise in malware. Sophisticated Android malware employ detection avoidance techniques in order to hide their malicious…

Cryptography and Security · Computer Science 2017-04-03 Mohammed K. Alzaylaee , Suleiman Y. Yerima , Sakir Sezer

Training pipelines for machine learning (ML) based malware classification often rely on crowdsourced threat feeds, exposing a natural attack injection point. In this paper, we study the susceptibility of feature-based ML malware classifiers…

Cryptography and Security · Computer Science 2021-01-12 Giorgio Severi , Jim Meyer , Scott Coull , Alina Oprea

Automated Machine Learning-based systems' integration into a wide range of tasks has expanded as a result of their performance and speed. Although there are numerous advantages to employing ML-based systems, if they are not interpretable,…

Machine Learning · Computer Science 2022-12-08 Ioannis Mollas , Nick Bassiliades , Grigorios Tsoumakas

This paper proposes a set of criteria to evaluate the objectiveness of explanation methods of neural networks, which is crucial for the development of explainable AI, but it also presents significant challenges. The core challenge is that…

Machine Learning · Computer Science 2019-11-21 Hao Zhang , Jiayi Chen , Haotian Xue , Quanshi Zhang

Machine learning systems have become popular in fields such as marketing, financing, or data mining. While they are highly accurate, complex machine learning systems pose challenges for engineers and users. Their inherent complexity makes…

Computers and Society · Computer Science 2019-07-31 Andrea Papenmeier , Gwenn Englebienne , Christin Seifert

An important problem of cyber-security is malware analysis. Besides good precision and recognition rate, a malware detection scheme needs to be able to generalize well for novel malware families (a.k.a zero-day attacks). It is important…

Cryptography and Security · Computer Science 2018-10-25 Mahmood Yousefi-Azar , Len Hamey , Vijay Varadharajan , Shiping Chen

Following the increasing popularity of mobile ecosystems, cybercriminals have increasingly targeted them, designing and distributing malicious apps that steal information or cause harm to the device's owner. Aiming to counter them,…

Cryptography and Security · Computer Science 2018-07-16 Lucky Onwuzurike , Mario Almeida , Enrico Mariconti , Jeremy Blackburn , Gianluca Stringhini , Emiliano De Cristofaro

Large language models (LLMs) are capable of generating plausible explanations of how they arrived at an answer to a question. However, these explanations can misrepresent the model's "reasoning" process, i.e., they can be unfaithful. This,…

Computation and Language · Computer Science 2025-05-21 Katie Matton , Robert Osazuwa Ness , John Guttag , Emre Kıcıman

Large language models (LLMs) are becoming more advanced and widespread and have shown their applicability to various domains, including cybersecurity. Static malware analysis is one of the most important tasks in cybersecurity; however, it…

Cryptography and Security · Computer Science 2024-11-25 Shota Fujii , Rei Yamagishi

Research into the explanation of machine learning models, i.e., explainable AI (XAI), has seen a commensurate exponential growth alongside deep artificial neural networks throughout the past decade. For historical reasons, explanation and…

Human-Computer Interaction · Computer Science 2020-09-29 Brittany Davis , Maria Glenski , William Sealy , Dustin Arendt

Android is undergoing unprecedented malicious threats daily, but the existing methods for malware detection often fail to cope with evolving camouflage in malware. To address this issue, we present HAWK, a new malware detection framework…

Cryptography and Security · Computer Science 2021-08-18 Yiming Hei , Renyu Yang , Hao Peng , Lihong Wang , Xiaolin Xu , Jianwei Liu , Hong Liu , Jie Xu , Lichao Sun