A Comprehensive Analysis of Factors Impacting Membership Inference

D Dealcala, G Mancera, A Morales… - Proceedings of the …, 2024 - openaccess.thecvf.com
We analyze various factors affecting the proper functioning of MIA and MINT two research
lines aimed at detecting data used for training. The difference between these lines lies in the …

Do Parameters Reveal More than Loss for Membership Inference?

A Suri, X Zhang, D Evans - arxiv preprint arxiv:2406.11544, 2024 - arxiv.org
Membership inference attacks aim to infer whether an individual record was used to train a
model, serving as a key tool for disclosure auditing. While such evaluations are useful to …

Second FRCSyn-onGoing: Winning Solutions and Post-Challenge Analysis to Improve Face Recognition with Synthetic Data

I DeAndres-Tame, R Tolosana, P Melzi… - arxiv preprint arxiv …, 2024 - arxiv.org
Synthetic data is gaining increasing popularity for face recognition technologies, mainly due
to the privacy concerns and challenges associated with obtaining real data, including …

Identity-Focused Inference and Extraction Attacks on Diffusion Models

J Vora, A Krishnan, N Bouacida, PRV Shankar… - arxiv preprint arxiv …, 2024 - arxiv.org
The increasing reliance on diffusion models for generating synthetic images has amplified
concerns about the unauthorized use of personal data, particularly facial images, in model …

[PDF][PDF] Cybersecurity Risks of AI

L Sivashanmugam, JE Tan - krinstitute.org
Artificial Intelligence (AI) as an emergent technology is progressing at breakneck speed.
Across the globe, we are starting to see AI systems 1 being trialled in critical infrastructure …