Results 1 to 10 of about 6,005,104 (327)
Using deep learning to solve computer security challenges: a survey [PDF]
Cybersecurity, 2020 Although using machine learning techniques to solve computer security challenges is not a new idea, the rapidly emerging Deep Learning technology has recently triggered a substantial amount of interests in the computer security community.
Yoon-Ho Choi +7 more
doaj +4 more sources
COMPUTER SECURITY AND SECURITY TECHNOLOGIES [PDF]
Journal of Process Management and New Technologies, 2013 With the increasing development of computer and communications technology growth and increasing needs and development of information systems security. The problem of security must be approached with greater caution.
Lazar Stošić, Dragan Veličković
doaj +3 more sources
Ethical Frameworks and Computer Security Trolley Problems: Foundations for Conversations [PDF]
USENIX Security Symposium, 2023 The computer security research community regularly tackles ethical questions. The field of ethics / moral philosophy has for centuries considered what it means to be"morally good"or at least"morally allowed / acceptable". Among philosophy's contributions
T. Kohno, Y. Acar, Wulf Loh
semanticscholar +1 more source
SoK: Explainable Machine Learning for Computer Security Applications [PDF]
European Symposium on Security and Privacy, 2022 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 ...
A. Nadeem +6 more
semanticscholar +1 more source
UNSW‐NB15 computer security dataset: Analysis through visualization [PDF]
Security and Privacy, 2021 Class imbalance refers to a major issue in data mining where data with unequal class distribution can deteriorate classification performance. Although it alone affects the performance of the classifiers, the joint‐effect of class imbalance and overlap is
Zeinab Zoghi, G. Serpen
semanticscholar +1 more source
Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks [PDF]
2024 IEEE Security and Privacy Workshops (SPW), 2023 Recent advances in instruction-following large language models (LLMs) have led to dramatic improvements in a range of NLP tasks. Unfortunately, we find that the same improved capabilities amplify the dual-use risks for malicious purposes of these models.
Daniel Kang +5 more
semanticscholar +1 more source
Informatics, 2023 Privacy-preserving computation (PPC) enables encrypted computation of private data. While advantageous in theory, the complex technology has steep barriers to entry in practice. Here, we derive design goals and principles for a middleware that encapsulates the demanding cryptography server side and provides a simple-to-use interface to client-side ...
Hendrik Ballhausen +1 more
openaire +2 more sources
Neural network based single index evaluation for SQL injection attack detection in health care data
Measurement: Sensors, 2023 In recent years, there are a lot of security risks in the network, and there is the combination intersection between the computer network security problems and security evaluation.
N. Nagabhooshanam +4 more
doaj +1 more source
Verifiable image revision from chameleon hashes
Cybersecurity, 2021 In a digital society, the rapid development of computer science and the Internet has greatly facilitated image applications. However, one of the public network also brings risks to both image tampering and privacy exposure.
Junpeng Xu +4 more
doaj +1 more source
COMPUTER NETWORK SECURITY [PDF]
Carpathian Journal of Electrical Engineering, 2023 Computers that we connect to a network serve to exchange data, which is located in the computer’s working memory. Data transmission can also be done through electronic signals, and these connections can be wireless networks or wired networks.
Marijan MIJATOVIĆ, Marko MIJATOVIĆ
doaj