In our work, the main conceptual result shows the other direction: a robust algorithm can be used to design a private algorithm. 7/n
ETHICS
-
Private Algorithms Automatically Guarantee Robustness Properties
By
–
I like these works, but it would be nice to see something based solely on robustness or privacy, rather than properties of the algorithms themselves. Here's a work by @kris_georgiev1 & @Samuel_BKH that shows private algorithms are automatically robust https://
arxiv.org/abs/2211.00724 6/n -
Formalizing Robustness and Privacy in Algorithm Design
By
–
Intuitively, robustness and privacy of an algorithm are closely related: they both say the algorithm should be somehow insensitive to changing a small amount of the dataset. Formalizing connections between the two has proven to be a bit trickier. 3/n
-
Private Estimators Framework: Dwork and Lei’s 2009 Breakthrough
By
–
This direction was kicked off by Dwork and Lei in 2009, who gave a framework for designing private estimators, which works especially well given robust ones (
https://
stat.cmu.edu/~jinglei/dl09.
pdf
…). But in just the last 2-3 years, there's been a lot more interest in finding connections. 4/n -
Robustness Implies Privacy in Statistical Estimation
By
–
New paper with @Samuel_BKH
, @mahbodm_
, and Shyam Narayanan: "Robustness Implies Privacy in Statistical Estimation." A robust estimator can be (black-box) converted to a private estimator, often optimally. https://
arxiv.org/abs/2212.05015 1/n -
Hand-coding fixes to machine-learned models ultimately fail
By
–
Hand-coding fixes to massive machine-learned models always fails in the end.
-
Humans fascinated by humanlike robots but robots indifferent to humans
By
–
Humans are fascinated by humanlike robots. Robots will have no interest whatsoever in robotlike humans.
-
The Irony of Writing About GPT: Human Content Remains Superior
By
–
This topic hasn't been written about much, so the language models still produce fairly straightforward ideas. I may have pulled some inspiration from them, but not much. The great irony of writing about GPT is that it's one area where the best content is going to be human-made
-
AI fears versus current algorithmic manipulation reality
By
–
“AI is gonna take over the world and brainwash all of us!!!” Meanwhile, simple probability distributions already control millions of people, manipulating their emotions, keeping them up all night, & destroying their lives.