5 papers
Membership and Memorization in LLM Knowledge Distillation
Ziqi Zhang, Ali Shahin Shamsabadi, Hanxiao Lu +2
Recent advances in Knowledge Distillation (KD) aim to mitigate the high computational demands of Large Language Models (LLMs) by transferring knowledge from a large ''teacher'' to…
Verifiable Unlearning on Edge
Mohammad M Maheri, Alex Davidson, Hamed Haddadi
Machine learning providers commonly distribute global models to edge devices, which subsequently personalize these models using local data. However, issues such as copyright infrin…
TeleSparse: Practical Privacy-Preserving Verification of Deep Neural Networks
Mohammad M Maheri, Hamed Haddadi, Alex Davidson
Verification of the integrity of deep learning inference is crucial for understanding whether a model is being applied correctly. However, such verification typically requires acce…
NoEsis: Differentially Private Knowledge Transfer in Modular LLM Adaptation
Rob Romijnders, Stefanos Laskaridis, Ali Shahin Shamsabadi +1
Large Language Models (LLM) are typically trained on vast amounts of data from various sources. Even when designed modularly (e.g., Mixture-of-Experts), LLMs can leak privacy on th…
Proof of Steak
Jon Crowcroft, Hamed Haddadi, Arthur Gervais +1
We introduce Proof-of-Steak (PoS) as a fundamental net-zero block generation technique, often accompanied by Non-Frangipane Tokens. Genesis cut is gradually heated and minted (usin…