DeepAI AI Chat
Log In Sign Up

Quantifying Program Bias

by   Aws Albarghouthi, et al.

With the range and sensitivity of algorithmic decisions expanding at a break-neck speed, it is imperative that we aggressively investigate whether programs are biased. We propose a novel probabilistic program analysis technique and apply it to quantifying bias in decision-making programs. Specifically, we (i) present a sound and complete automated verification technique for proving quantitative properties of probabilistic programs; (ii) show that certain notions of bias, recently proposed in the fairness literature, can be phrased as quantitative correctness properties; and (iii) present FairSquare, the first verification tool for quantifying program bias, and evaluate it on a range of decision-making programs.


page 1

page 2

page 3

page 4


Fairness as a Program Property

We explore the following question: Is a decision-making program fair, fo...

ProbTA: A sound and complete proof rule for probabilistic verification

We propose a sound and complete proof rule ProbTA for quantitative analy...

Reductions for Safety Proofs (Extended Version)

Program reductions are used widely to simplify reasoning about the corre...

Quantitative Verification of Opacity Properties in Security Systems

We delineate a methodology for the specification and verification of flo...

Relatively Complete Verification of Probabilistic Programs

We study a syntax for specifying quantitative "assertions" - functions m...

Kantorovich Continuity of Probabilistic Programs

The Kantorovich metric is a canonical lifting of a distance from sets to...

Proving Expected Sensitivity of Probabilistic Programs with Randomized Execution Time

The notion of program sensitivity (aka Lipschitz continuity) specifies t...