~/talk

On Low End Obfuscation and Learning

links:none on file
slides:none on file

Shows an exact characterization: a program class admits information‑theoretic (perfect) obfuscation exactly when it is whitebox learning–exactly learnable from representation‑dependent hints, and proper obfuscation corresponds to proper learning. Gives a quasi‑polynomial canonicalization algorithm for decision trees. Proves a concrete impossibility: assuming one‑way functions, there is no polynomial‑time proper indistinguishability obfuscator mapping into 3‑CNF (and more generally no obfuscation into any class whose dual is PAC‑learnable). Also separates deterministic, perfect and randomized notions via random self‑reductions.

AI-written summary · about

  1. 0:00Intro
  2. 0:27Program Obfuscation
  3. 2:16Indistinguishability Obfuscation
  4. 5:10Does (computational) iO exist?
  5. 6:34Does statistical iO exist?
  6. 7:09This work: "Low-End" Obfuscation
  7. 8:16"Low-End" Obfuscation - why?
  8. 12:27Exact learning implies (information theoretic) iO
  9. 19:16Characterizing Information-Theoretic iO
  10. 25:48Learning in the mistake bound model
  11. 28:29PAC Learning for Negative Results
  12. 32:42Result 3: Separating Notions of Information-Theoretic iO
  13. 41:46Open problems
~/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.