Proceedings ArticleDOI
Trustworthy AI
TLDR
The tutorial on “Trustworthy AI” is proposed to address six critical issues in enhancing user and public trust in AI systems, namely: bias and fairness, explainability, robust mitigation of adversarial attacks, improved privacy and security in model building, and being decent.Abstract:
Modern AI systems are reaping the advantage of novel learning methods. With their increasing usage, we are realizing the limitations and shortfalls of these systems. Brittleness to minor adversarial changes in the input data, ability to explain the decisions, address the bias in their training data, high opacity in terms of revealing the lineage of the system, how they were trained and tested, and under which parameters and conditions they can reliably guarantee a certain level of performance, are some of the most prominent limitations. Ensuring the privacy and security of the data, assigning appropriate credits to data sources, and delivering decent outputs are also required features of an AI system. We propose the tutorial on “Trustworthy AI” to address six critical issues in enhancing user and public trust in AI systems, namely: (i) bias and fairness, (ii) explainability, (iii) robust mitigation of adversarial attacks, (iv) improved privacy and security in model building, (v) being decent, and (vi) model attribution, including the right level of credit assignment to the data sources, model architectures, and transparency in lineage.read more
Citations
More filters
Proceedings ArticleDOI
Assessing the Alignment of Social Robots with Trustworthy AI Design Guidelines: A Preliminary Research Study
TL;DR: In this article, the authors explored flaws within the robot's system, and analyzed these flaws to assess the overall alignment of the robot system design with the IEEE global standards on the design of ethically aligned trustworthy autonomous intelligent systems (IEEE A/IS Standards).
Posted Content
Socially Responsible AI Algorithms: Issues, Purposes, and Challenges
TL;DR: In this article, the authors provide a systematic framework of socially responsible AI algorithms and discuss how to leverage this framework to improve societal well-being through protection, information, and prevention/mitigation.
Proceedings ArticleDOI
Ethics of Trust/worthiness in Autonomous Systems: a scoping review.
TL;DR: In this paper , a scoping review surveys the literature to identify the problematic nature of adaptive autonomous systems with evolving functionality (AASEFs), the ethical worries that they generate, and the ethical principles affected.
References
More filters
Journal ArticleDOI
Adversarial Examples: Attacks and Defenses for Deep Learning
TL;DR: In this paper, the authors review recent findings on adversarial examples for DNNs, summarize the methods for generating adversarial samples, and propose a taxonomy of these methods.
Proceedings ArticleDOI
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks.
Weilin Xu,David Evans,Yanjun Qi +2 more
Abstract: Although deep neural networks (DNNs) have achieved great success in many tasks, they can often be fooled by \emph{adversarial examples} that are generated by adding small but purposeful distortions to natural examples. Previous studies to defend against adversarial examples mostly focused on refining the DNN models, but have either shown limited success or required expensive computation. We propose a new strategy, \emph{feature squeezing}, that can be used to harden DNN models by detecting adversarial examples. Feature squeezing reduces the search space available to an adversary by coalescing samples that correspond to many different feature vectors in the original space into a single sample. By comparing a DNN model's prediction on the original input with that on squeezed inputs, feature squeezing detects adversarial examples with high accuracy and few false positives. This paper explores two feature squeezing methods: reducing the color bit depth of each pixel and spatial smoothing. These simple strategies are inexpensive and complementary to other defenses, and can be combined in a joint detection framework to achieve high detection rates against state-of-the-art attacks.
Journal ArticleDOI
Adversarial Attacks and Defenses in Deep Learning
TL;DR: The theoretical foundations, algorithms, and applications of adversarial attack techniques are introduced and a few research efforts on the defense techniques are described, which cover the broad frontier in the field.
Journal ArticleDOI
Bias in data-driven artificial intelligence systems—An introductory survey
Eirini Ntoutsi,Pavlos Fafalios,Ujwal Gadiraju,Vasileios Iosifidis,Wolfgang Nejdl,Maria-Esther Vidal,Salvatore Ruggieri,Franco Turini,Symeon Papadopoulos,Emmanouil Krasanakis,Ioannis Kompatsiaris,Katharina Kinder-Kurlanda,Claudia Wagner,Fariba Karimi,Miriam Fernandez,Harith Alani,Bettina Berendt,Bettina Berendt,Tina Kruegel,Christian Heinze,Klaus Broelemann,Gjergji Kasneci,Thanassis Tiropanis,Steffen Staab,Steffen Staab,Steffen Staab +25 more
TL;DR: A broad multidisciplinary overview of the area of bias in AI systems is provided, focusing on technical challenges and solutions as well as to suggest new research directions towards approaches well‐grounded in a legal frame.
Proceedings ArticleDOI
SafetyNet: Detecting and Rejecting Adversarial Examples Robustly
TL;DR: In this paper, the authors describe a method to produce a network where current methods such as DeepFool have great difficulty producing adversarial samples, and provide a reasonable analyses that their construction is difficult to defeat, and show experimentally that their method is hard to defeat with both Type I and Type II attacks using several standard networks and datasets.
Related Papers (5)
Achieving Differential Privacy and Fairness in Logistic Regression
Depeng Xu,Shuhan Yuan,Xintao Wu +2 more