Related papers: Candidate Software Process Flaws for the Boeing 73…
Online experiments (A/B tests) are widely regarded as the gold standard for evaluating recommender system variants and guiding launch decisions. However, a variety of biases can distort the results of the experiment and mislead…
On the January 22nd 2019, Airbus launched a quantum computing challenge to solve a set of problems relevant for the aircraft life cycle…
Recent successes in the Machine Learning community have led to a steep increase in the number of papers submitted to conferences. This increase made more prominent some of the issues that affect the current review process used by these…
Automated recruitment tools are proliferating. While having the promise of improving efficiency, various risks, including bias, challenges the potential of these tools. An in-depth understanding of the perceived risk factors and needs from…
This two part paper argues that seemingly "technical" choices made by developers of machine-learning based algorithmic tools used to inform decisions by criminal justice authorities can create serious constitutional dangers, enhancing the…
Model mismatch and process noise are two frequently occurring phenomena that can drastically affect the performance of model predictive control (MPC) in practical applications. We propose a principled way to tune the cost function and the…
BCI algorithm development has long been hampered by two major issues: small sample sets and a lack of reproducibility. We offer a solution to both of these problems via a software suite that streamlines both the issues of finding and…
As modern software systems continue inexorably to increase in complexity and capability, users have become accustomed to periodic cycles of updating and upgrading to avoid obsolescence -- if at some cost in terms of frustration. In the case…
We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through scheming. Scheming is a potential threat model where AI…
Instances of Artificial Intelligence (AI) systems failing to deliver consistent, satisfactory performance are legion. We investigate why AI failures occur. We address only a narrow subset of the broader field of AI Safety. We focus on AI…
We discuss the computational complexity and feasibility properties of scenario based techniques for uncertain optimization programs. We consider different solution alternatives ranging from the standard scenario approach to recursive…
Algorithmic recourse provides explanations that help users overturn an unfavorable decision by a machine learning system. But so far very little attention has been paid to whether providing recourse is beneficial or not. We introduce an…
This paper analyzes and compares 11 different proposals for building safe advanced AI under the current machine learning paradigm, including major contenders such as iterated amplification, AI safety via debate, and recursive reward…
Software engineering faces a fundamental challenge: multi-agent AI systems fail in ways that defy explanation by traditional theories. While individual agents perform correctly, their interactions degrade entire ecosystems, revealing a gap…
Automated decision systems are increasingly used for consequential decision making -- for a variety of reasons. These systems often rely on sophisticated yet opaque models, which do not (or hardly) allow for understanding how or why a given…
With the increasing complexity of software permeating critical domains such as autonomous driving, new challenges are emerging in the ways the engineering of these systems needs to be rethought. Autonomous driving is expected to continue…
Context. Algorithmic racism is the term used to describe the behavior of technological solutions that constrains users based on their ethnicity. Lately, various data-driven software systems have been reported to discriminate against Black…
In this paper, we ask the question of why the quality of commercial software, in terms of security and safety, does not measure up to that of other (durable) consumer goods we have come to expect. We examine this question through the lens…
We present a safety verification framework for design-time and run-time assurance of learning-based components in aviation systems. Our proposed framework integrates two novel methodologies. From the design-time assurance perspective, we…
We study the problem of troubleshooting machine learning systems that rely on analytical pipelines of distinct components. Understanding and fixing errors that arise in such integrative systems is difficult as failures can occur at multiple…