~/talk

Design and Evaluation of a Data-Driven Password Meter

on YouTube 19m
Talkat CHI 2017 · 2017-05-06..05-11· [security, machine-learning]

speakers

name:Blase Ur
links:none on file
name:Felicia Alfieri
links:none on file
name:Maung Aung
links:none on file
name:Lujo Bauer
links:none on file
name:Nicolas Christin
links:none on file
name:Jessica Colnago
links:none on file
name:Lorrie Faith Cranor
linkedin:lorriecranor
name:Henry Dixon
links:none on file
name:Pardis Emami-Naeini
links:none on file
name:Hana Habib
links:none on file
name:Noah Johnson
links:none on file
name:William Melicher
links:none on file

resources

video:https://youtu.be/EUorslghNaE
slides:none on file

summary

A client-side password meter combines compact neural networks to estimate guessability with a regression-weighted set of 21 characteristics that generate concrete text feedback and suggested password edits. A 4,509-participant online experiment finds the data-driven meter yields materially stronger passwords under a common 8-character composition policy while memorability does not decrease. Code and a live demo are open-sourced, and the meter runs with only a few megabytes sent to the browser.

AI-written summary · about

chapters (6)

  1. 0:00Start
  2. 2:07How Do We Provide Data-Driven Feedback to Users
  3. 6:36Password Composition
  4. 7:03Stringency of Scoring
  5. 8:32Public Non Sensitive Feedback
  6. 12:22Participant Sentiment

related talks

~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.