Zobrazeno 1 - 10
of 307
pro vyhledávání: '"HADDADI, HAMED"'
Autor:
Cadet, Xavier F., Borovykh, Anastasia, Malekzadeh, Mohammad, Ahmadi-Abhari, Sara, Haddadi, Hamed
Machine unlearning (MU) aims to remove the influence of particular data points from the learnable parameters of a trained machine learning model. This is a crucial capability in light of data privacy requirements, trustworthiness, and safety in deplo
Externí odkaz:
http://arxiv.org/abs/2410.01276
Though there is much interest in fair AI systems, the problem of fairness noncompliance -- which concerns whether fair models are used in practice -- has received lesser attention. Zero-Knowledge Proofs of Fairness (ZKPoF) address fairness noncomplia
Externí odkaz:
http://arxiv.org/abs/2410.02777
We present Nebula, a system for differential private histogram estimation of data distributed among clients. Nebula enables clients to locally subsample and encode their data such that an untrusted server learns only data values that meet an aggregat
Externí odkaz:
http://arxiv.org/abs/2409.09676
Prior Membership Inference Attacks (MIAs) on pre-trained Large Language Models (LLMs), adapted from classification model attacks, fail due to ignoring the generative process of LLMs across token sequences. In this paper, we present a novel attack tha
Externí odkaz:
http://arxiv.org/abs/2409.13745
Autor:
Nazemi, Niousha, Tavallaie, Omid, Chen, Shuaijun, Mandalari, Anna Maria, Thilakarathna, Kanchana, Holz, Ralph, Haddadi, Hamed, Zomaya, Albert Y.
Federated Learning (FL) is a promising distributed learning framework designed for privacy-aware applications. FL trains models on client devices without sharing the client's data and generates a global model on a server by aggregating model updates.
Externí odkaz:
http://arxiv.org/abs/2409.01722
Autor:
Nazemi, Niousha, Tavallaie, Omid, Mandalari, Anna Maria, Haddadi, Hamed, Holz, Ralph, Zomaya, Albert Y.
This paper investigates the impact of internet centralization on DNS provisioning, particularly its effects on vulnerable populations such as the indigenous people of Australia. We analyze the DNS dependencies of Australian government domains that se
Externí odkaz:
http://arxiv.org/abs/2408.12958
We present the first measurement of the user-effect and privacy impact of "Related Website Sets," a recent proposal to reduce browser privacy protections between two sites if those sites are related to each other. An assumption (both explicitly and i
Externí odkaz:
http://arxiv.org/abs/2408.07495
In-situ sensing devices need to be deployed in remote environments for long periods of time; minimizing their power consumption is vital for maximising both their operational lifetime and coverage. We introduce Terracorder -- a versatile multi-sensor
Externí odkaz:
http://arxiv.org/abs/2408.02407
Personalized learning is a proposed approach to address the problem of data heterogeneity in collaborative machine learning. In a decentralized setting, the two main challenges of personalization are client clustering and data privacy. In this paper,
Externí odkaz:
http://arxiv.org/abs/2405.17697
Large language models (LLMs) have demonstrated remarkable capabilities across various domains, although their susceptibility to hallucination poses significant challenges for their deployment in critical areas such as healthcare. To address this issu
Externí odkaz:
http://arxiv.org/abs/2405.06545