Related papers: Explainable AI for Natural Adversarial Images

Explainable AI for Natural Adversarial Images

URL: http://arxiv.org/abs/2106.09106v1
Date: Wed, 16 Jun 2021 20:19:04 GMT
Title: Explainable AI for Natural Adversarial Images
Authors: Tomas Folke, ZhaoBin Li, Ravi B. Sojitra, Scott Cheng-Hsin Yang, and Patrick Shafto
Abstract summary: Humans tend to assume that the AI's decision process mirrors their own. Here we evaluate if methods from explainable AI can disrupt this assumption to help participants predict AI classifications for adversarial and standard images. We find that both saliency maps and examples facilitate catching AI errors, but their effects are not additive, and saliency maps are more effective than examples.
Score: 4.387699521196243
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Adversarial images highlight how vulnerable modern image classifiers are to perturbations outside of their training set. Human oversight might mitigate this weakness, but depends on humans understanding the AI well enough to predict when it is likely to make a mistake. In previous work we have found that humans tend to assume that the AI's decision process mirrors their own. Here we evaluate if methods from explainable AI can disrupt this assumption to help participants predict AI classifications for adversarial and standard images. We find that both saliency maps and examples facilitate catching AI errors, but their effects are not additive, and saliency maps are more effective than examples.

Related papers

Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images [66.20578637253831]
There is a growing concern that the advancement of artificial intelligence (AI) technology may produce fake photos. This study aims to comprehensively evaluate agents for distinguishing state-of-the-art AI-generated visual content.
arXiv Detail & Related papers (2023-04-25T17:51:59Z)
Fairness in AI and Its Long-Term Implications on Society [68.8204255655161]
We take a closer look at AI fairness and analyze how lack of AI fairness can lead to deepening of biases over time. We discuss how biased models can lead to more negative real-world outcomes for certain groups. If the issues persist, they could be reinforced by interactions with other risks and have severe implications on society in the form of social unrest.
arXiv Detail & Related papers (2023-04-16T11:22:59Z)
Improving Human-AI Collaboration With Descriptions of AI Behavior [14.904401331154062]
People work with AI systems to improve their decision making, but often under- or over-rely on AI predictions and perform worse than they would have unassisted. To help people appropriately rely on AI aids, we propose showing them behavior descriptions.
arXiv Detail & Related papers (2023-01-06T00:33:08Z)
Seamful XAI: Operationalizing Seamful Design in Explainable AI [59.89011292395202]
Mistakes in AI systems are inevitable, arising from both technical limitations and sociotechnical gaps. We propose that seamful design can foster AI explainability by revealing sociotechnical and infrastructural mismatches. We explore this process with 43 AI practitioners and real end-users.
arXiv Detail & Related papers (2022-11-12T21:54:05Z)
Cybertrust: From Explainable to Actionable and Interpretable AI (AI2) [58.981120701284816]
Actionable and Interpretable AI (AI2) will incorporate explicit quantifications and visualizations of user confidence in AI recommendations. It will allow examining and testing of AI system predictions to establish a basis for trust in the systems' decision making.
arXiv Detail & Related papers (2022-01-26T18:53:09Z)
The Who in XAI: How AI Background Shapes Perceptions of AI Explanations [61.49776160925216]
We conduct a mixed-methods study of how two different groups--people with and without AI background--perceive different types of AI explanations. We find that (1) both groups showed unwarranted faith in numbers for different reasons and (2) each group found value in different explanations beyond their intended design.
arXiv Detail & Related papers (2021-07-28T17:32:04Z)
The Threat of Offensive AI to Organizations [52.011307264694665]
This survey explores the threat of offensive AI on organizations. First, we discuss how AI changes the adversary's methods, strategies, goals, and overall attack model. Then, through a literature review, we identify 33 offensive AI capabilities which adversaries can use to enhance their attacks.
arXiv Detail & Related papers (2021-06-30T01:03:28Z)
Mitigating belief projection in explainable artificial intelligence via Bayesian Teaching [4.864819846886143]
Explainable AI (XAI) attempts to improve human understanding but rarely accounts for how people typically reason about unfamiliar agents. We propose explicitly modeling the human explainee via Bayesian Teaching, which evaluates explanations by how much they shift explainees' inferences toward a desired goal.
arXiv Detail & Related papers (2021-02-07T21:23:24Z)
Does Explainable Artificial Intelligence Improve Human Decision-Making? [17.18994675838646]
We compare and evaluate objective human decision accuracy without AI (control), with an AI prediction (no explanation) and AI prediction with explanation. We find any kind of AI prediction tends to improve user decision accuracy, but no conclusive evidence that explainable AI has a meaningful impact. Our results indicate that, at least in some situations, the "why" information provided in explainable AI may not enhance user decision-making.
arXiv Detail & Related papers (2020-06-19T15:46:13Z)
Cognitive Anthropomorphism of AI: How Humans and Computers Classify Images [0.0]
Humans engage in cognitive anthropomorphism: expecting AI to have the same nature as human intelligence. This mismatch presents an obstacle to appropriate human-AI interaction. I offer three strategies for system design that can address the mismatch between human and AI classification.
arXiv Detail & Related papers (2020-02-07T21:49:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.