On Security and Sparsity of Linear Classifiers for Adversarial Settings
원문 초록
Machine-learning techniques are widely used in security-related applications, like spam and malware detection. However, in such settings, they have been shown to be vulnerable to adversarial attacks, including the deliberate manipulation of data at test time to evade detection. In this work, we focus on the vulnerability of linear classifiers to evasion attacks. This can be considered a relevant problem, as linear classifiers have been increasingly used in embedded systems and mobile devices for their low processing time and memory requirements. We exploit recent findings in robust optimization to investigate the link between regularization and security of linear classifiers, depending on the type of attack. We also analyze the relationship between the sparsity of feature weights, which is desirable for reducing processing cost, and the security of linear classifiers. We further propose a novel octagonal regularizer that allows us to achieve a proper trade-off between them. Finally, we empirically show how this regularizer can improve classifier security and sparsity in real-world application examples including spam and malware detection.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
EMBER2024 -- A Benchmark Dataset for Holistic Evaluation of Malware Classifiers
LAMDA: A Longitudinal Android Malware Benchmark for Concept Drift Analysis
Evaluating the Robustness of Adversarial Defenses in Malware Detection Systems
Cyber Security Data Science: Machine Learning Methods and their Performance on Imbalanced Datasets
Imbalanced malware classification: an approach based on dynamic classifier selection
CyberLLMInstruct: A New Dataset for Analysing Safety of Fine-Tuned LLMs Using Cyber Security Data
토론
이 논문과 연결된 포럼 글이 아직 없습니다.