Yara Elias

Rasoul Shahsavarifar, Jithu Chandran, Mario Inchiosa et al.

In the past few years, Artificial Intelligence (AI) has garnered attention from various industries including financial services (FS). AI has made a positive impact in financial services by enhancing productivity and improving risk management. While AI can offer efficient solutions, it has the potential to bring unintended consequences. One such consequence is the pronounced effect of AI-related unfairness and attendant fairness-related harms. These fairness-related harms could involve differential treatment of individuals; for example, unfairly denying a loan to certain individuals or groups of individuals. In this paper, we focus on identifying and mitigating individual unfairness and leveraging some of the recently published techniques in this domain, especially as applicable to the credit adjudication use case. We also investigate the extent to which techniques for achieving individual fairness are effective at achieving group fairness. Our main contribution in this work is functionalizing a two-step training process which involves learning a fair similarity metric from a group sense using a small portion of the raw data and training an individually "fair" classifier using the rest of the data where the sensitive features are excluded. The key characteristic of this two-step technique is related to its flexibility, i.e., the fair metric obtained in the first step can be used with any other individual fairness algorithms in the second step. Furthermore, we developed a second metric (distinct from the fair similarity metric) to determine how fairly a model is treating similar individuals. We use this metric to compare a "fair" model against its baseline model in terms of their individual fairness value. Finally, some experimental results corresponding to the individual unfairness mitigation techniques are presented.

Yara Elias, Kristin E. Lauter, Ekin Ozman et al.

In this paper, we survey the status of attacks on the ring and polynomial learning with errors problems (RLWE and PLWE). Recent work on the security of these problems [Eisenträger-Hallgren-Lauter, Elias-Lauter-Ozman-Stange] gives rise to interesting questions about number fields. We extend these attacks and survey related open problems in number theory, including spectral distortion of an algebraic number and its relationship to Mahler measure, the monogenic property for the ring of integers of a number field, and the size of elements of small order modulo q.

Yara Elias, Kristin E. Lauter, Ekin Ozman et al.

The ring and polynomial learning with errors problems (Ring-LWE and Poly-LWE) have been proposed as hard problems to form the basis for cryptosystems, and various security reductions to hard lattice problems have been presented. So far these problems have been stated for general (number) rings but have only been closely examined for cyclotomic number rings. In this paper, we state and examine the Ring-LWE problem for general number rings and demonstrate provably weak instances of Ring-LWE. We construct an explicit family of number fields for which we have an efficient attack. We demonstrate the attack in both theory and practice, providing code and running times for the attack. The attack runs in time linear in q, where q is the modulus. Our attack is based on the attack on Poly-LWE which was presented in [Eisenträger-Hallgren-Lauter]. We extend the EHL-attack to apply to a larger class of number fields, and show how it applies to attack Ring-LWE for a heuristically large class of fields. Certain Ring-LWE instances can be transformed into Poly-LWE instances without distorting the error too much, and thus provide the first weak instances of the Ring-LWE problem. We also provide additional examples of fields which are vulnerable to our attacks on Poly-LWE, including power-of-$2$ cyclotomic fields, presented using the minimal polynomial of $ζ_{2^n} \pm 1$.