paper-with-me

홈 › Papers

Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm?

2024-09-05 · Rui Wen, Michael Backes, Yang Zhang

Machine learning has revolutionized numerous domains, playing a crucial role in driving advancements and enabling data-centric processes. The significance of data in training models and shaping their performance cannot be overstated. Recent research has highlighted the heterogeneous impact of individual data samples, particularly the presence of valuable data that significantly contributes to the utility and effectiveness of machine learning models. However, a critical question remains unanswered: are these valuable data samples more vulnerable to machine learning attacks? In this work, we investigate the relationship between data importance and machine learning attacks by analyzing five distinct attack types. Our findings reveal notable insights. For example, we observe that high importance data samples exhibit increased vulnerability in certain attacks, such as membership inference and model stealing. By analyzing the linkage between membership inference vulnerability and data importance, we demonstrate that sample characteristics can be integrated into membership metrics by introducing sample-specific criteria, therefore enhancing the membership inference performance. These findings emphasize the urgent need for innovative defense mechanisms that strike a balance between maximizing utility and safeguarding valuable data against potential exploitation.

📄 PDF Abstract BibTeX arXiv:2409.03741

Code (1)

TrustAIRLab/importance-in-mlattacks 공식 구현 pytorch

Similar Papers 제목 키워드 기반

On the Lack of Robustness of Binary Function Similarity Systems

2024-12-05 · Gianluca Capozzi, Tong Tang, Jie Wan, Ziqi Yang 외

Binary function similarity, which often relies on learning-based algorithms to identify what functions in a pool are most similar to a given query function, is a sought-after topic in different communities, including mac…

Malware AnalysisVulnerability Detection

Security Analysis of Deep Neural Networks Operating in the Presence of Cache Side-Channel Attacks

2018-10-08 · ICLR 2019 5 · Sanghyun Hong, Michael Davinroy, Yiǧitcan Kaya, Stuart Nevans Locke 외

Recent work has introduced attacks that extract the architecture information of deep neural networks (DNN), as this knowledge enhances an adversary's capability to conduct black-box attacks against the model. This paper …

Transfer Learning

Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models

2017-12-12 · ICLR 2018 1 · Wieland Brendel, Jonas Rauber, Matthias Bethge

Many machine learning algorithms are vulnerable to almost imperceptible perturbations of their inputs. So far it was unclear how much risk adversarial perturbations carry for the safety of real-world machine learning app…

BIG-bench Machine Learning

Exploring Feature Importance and Explainability Towards Enhanced ML-Based DoS Detection in AI Systems

2024-11-04 · Paul Badu Yakubu, Evans Owusu, Lesther Santana, Mohamed Rahouti 외

Denial of Service (DoS) attacks pose a significant threat in the realm of AI systems security, causing substantial financial losses and downtime. However, AI systems' high computational demands, dynamic behavior, and dat…

Feature EngineeringFeature Importancefeature selection

Demystifying Poisoning Backdoor Attacks from a Statistical Perspective

2023-10-16 · Ganghua Wang, Xun Xian, Jayanth Srinivasa, Ashish Kundu 외

The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety. Backdoor attacks pose a significant security risk due to their stealthy nature and…

Backdoor Attack