Daily, Monday 25 November 2024
Reconstructed on 19 November 2026 from archived source metadata.
From the editor
The editor's note for this issue is not available. The developments below were selected and ranked automatically from the sources listed.
Top developments
- 1
Hide in Plain Sight: Clean-Label Backdoor for Auditing Membership Inference
Membership inference attacks (MIAs) are critical tools for assessing privacy risks and ensuring compliance with regulations like the General Data Protection Regulation (GDPR). However, their potential for auditing unauthorized use of data remains under explored. To bridge this…
- 2
Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models
Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. While Differential Privacy (DP) offers a solution to mitigate these risks, it introduces significant computational and…
Advisories in this window
- 1 PyPI advisory1 high
This edition
2 developments and 1 advisories in the window. Selection and order are automatic: how stories are placed and ranked.