[HTML][HTML] Adversarial machine learning in industry: A systematic literature review

FV Jedrzejewski, L Thode, J Fischbach, T Gorschek… - Computers & …, 2024 - Elsevier
Abstract Adversarial Machine Learning (AML) discusses the act of attacking and defending
Machine Learning (ML) Models, an essential building block of Artificial Intelligence (AI). ML …

Everyone for themselves? a qualitative study about individual security setups of open source software contributors

S Amft, S Höltervennhoff, R Panskus… - … IEEE Symposium on …, 2024 - ieeexplore.ieee.org
To increase open-source software supply chain security, protecting the development
environment of contributors against attacks is crucial. For example, contributors must protect …

Engaging Company Developers in Security Research Studies: A Comprehensive Literature Review and Quantitative Survey

R Serafini, SA Horstmann, A Naiakshina - 33rd USENIX Security …, 2024 - usenix.org
Previous research demonstrated that company developers excel compared to freelancers
and computer science students, with the corporate environment significantly influencing …

It's like flossing your teeth: On the importance and challenges of reproducible builds for software supply chain security

M Fourné, D Wermke, W Enck, S Fahl… - 2023 IEEE Symposium …, 2023 - ieeexplore.ieee.org
The 2020 Solarwinds attack was a tipping point that caused a heightened awareness about
the security of the software supply chain and in particular the large amount of trust placed in …

Everybody's got ML, tell me what else you have: Practitioners' perception of ML-based security tools and explanations

J Mink, H Benkraouda, L Yang, A Ciptadi… - … IEEE Symposium on …, 2023 - ieeexplore.ieee.org
Significant efforts have been investigated to develop machine learning (ML) based tools to
support security operations. However, they still face key challenges in practice. A generally …

A method to facilitate membership inference attacks in deep learning models

Z Chen, K Pattabiraman - arXiv preprint arXiv:2407.01919, 2024 - arxiv.org
Modern machine learning (ML) ecosystems offer a surging number of ML frameworks and
code repositories that can greatly facilitate the development of ML models. Today, even …

FDI: Attack Neural Code Generation Systems through User Feedback Channel

Z Sun, X Du, X Luo, F Song, D Lo, L Li - Proceedings of the 33rd ACM …, 2024 - dl.acm.org
Neural code generation systems have recently attracted increasing attention to improve
developer productivity and speed up software development. Typically, these systems …

Architectural neural backdoors from first principles

H Langford, I Shumailov, Y Zhao, R Mullins… - arXiv preprint arXiv …, 2024 - arxiv.org
While previous research backdoored neural networks by changing their parameters, recent
work uncovered a more insidious threat: backdoors embedded within the definition of the …

Skipping the Security Side Quests: A Qualitative Study on Security Practices and Challenges in Game Development

P Klostermeyer, S Amft, S Höltervennhoff… - Proceedings of the …, 2024 - dl.acm.org
The video game market is one of the biggest for software products. Video game
development has progressed in the last decades to complex and multifaceted endeavors …

Interdisciplinary Approaches to Cybervulnerability Impact Assessment for Energy Critical Infrastructure

A Gallardo, R Erbes, K Le Blanc, L Bauer… - Proceedings of the CHI …, 2024 - dl.acm.org
As energy infrastructure becomes more interconnected, understanding cybersecurity risks to
production systems requires integrating operational and computer security knowledge. We …