Search Results for author:
Found 7 papers, 1 papers with code
Efficient Toxic Content Detection by Bootstrapping and Distilling Large Language Models
Furthermore, student LMs fine-tuned with rationales extracted via DToT outperform baselines on all datasets with up to 16. 9\% accuracy improvement, while being more than 60x smaller than conventional LLMs.
FireFly A Synthetic Dataset for Ember Detection in Wildfire
This paper presents "FireFly", a synthetic dataset for ember detection created using Unreal Engine 4 (UE4), designed to overcome the current lack of ember-specific training resources.
How Much Privacy Does Federated Learning with Secure Aggregation Guarantee?
While SA ensures no additional information is leaked about the individual model update beyond the aggregated model update, there are no formal guarantees on how much privacy FL with SA can actually offer; as information about the individual dataset can still potentially leak through the aggregated model computed at the server.
A Unified Prediction Framework for Signal Maps
This improves prediction (e. g., from 64% to 94% in recall for coverage loss) by removing points with negative values, and can also enable data minimization.
Privacy-Utility Trades in Crowdsourced Signal Map Obfuscation
Cellular providers and data aggregating companies crowdsource celluar signal strength measurements from user devices to generate signal maps, which can be used to improve network performance.
Location Leakage in Federated Signal Maps
We consider the problem of predicting cellular network performance (signal maps) from measurements collected by several mobile devices.
HARPO: Learning to Subvert Online Behavioral Advertising
Online behavioral advertising, and the associated tracking paraphernalia, poses a real privacy threat.
