Privacy side channels in machine learning systems
Most current approaches for protecting privacy in machine learning (ML) assume that
models exist in a vacuum, when in reality, ML models are part of larger systems that include …
models exist in a vacuum, when in reality, ML models are part of larger systems that include …
Algorithmic Complexity Attacks on Dynamic Learned Indexes
R Yang, EM Kornaropoulos, Y Cheng - arXiv preprint arXiv:2403.12433, 2024 - arxiv.org
Learned Index Structures (LIS) view a sorted index as a model that learns the data
distribution, takes a data element key as input, and outputs the predicted position of the key …
distribution, takes a data element key as input, and outputs the predicted position of the key …
Machine Learning for Out of Distribution Database Workloads
P Negi - 2024 - dspace.mit.edu
DBMS query optimizers are designed using several heuristics to make decisions, such as
simplifying assumptions in cardinality estimation, or cost model assumptions for predicting …
simplifying assumptions in cardinality estimation, or cost model assumptions for predicting …