SkillBot: Identifying Risky Content for Children in Alexa Skills

• URL: http://arxiv.org/abs/2102.03382v1
• Date: Fri, 5 Feb 2021 19:07:39 GMT
• Title: SkillBot: Identifying Risky Content for Children in Alexa Skills
• Authors: Tu Le, Danny Yuxing Huang, Noah Apthorpe, Yuan Tian
• Abstract summary: Children benefit from the rich functionalities of VPAs but are also exposed to new risks in the VPA ecosystem. We build a Natural Language Processing-based system to automatically interact with VPA apps. We identify 28 child-directed apps with risky contents and maintain a growing dataset of 31,966 non-overlapping app behaviors.
• Score: 4.465104643266321
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many households include children who use voice personal assistants (VPA) such as Amazon Alexa. Children benefit from the rich functionalities of VPAs and third-party apps but are also exposed to new risks in the VPA ecosystem (e.g., inappropriate content or information collection). To study the risks VPAs pose to children, we build a Natural Language Processing (NLP)-based system to automatically interact with VPA apps and analyze the resulting conversations to identify contents risky to children. We identify 28 child-directed apps with risky contents and maintain a growing dataset of 31,966 non-overlapping app behaviors collected from 3,434 Alexa apps. Our findings suggest that although voice apps designed for children are subject to more policy requirements and intensive vetting, children are still vulnerable to risky content. We then conduct a user study showing that parents are more concerned about VPA apps with inappropriate content than those that ask for personal information, but many parents are not aware that risky apps of either type exist. Finally, we identify a new threat to users of VPA apps: confounding utterances, or voice commands shared by multiple apps that may cause a user to invoke or interact with a different app than intended. We identify 4,487 confounding utterances, including 581 shared by child-directed and non-child-directed apps.

Related papers

• PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action [54.11479432110771]
  PrivacyLens is a novel framework designed to extend privacy-sensitive seeds into expressive vignettes and further into agent trajectories. We instantiate PrivacyLens with a collection of privacy norms grounded in privacy literature and crowdsourced seeds. State-of-the-art LMs, like GPT-4 and Llama-3-70B, leak sensitive information in 25.68% and 38.69% of cases, even when prompted with privacy-enhancing instructions.
  arXiv  Detail & Related papers  (2024-08-29T17:58:38Z)
• "Don't forget to put the milk back!" Dataset for Enabling Embodied Agents to Detect Anomalous Situations [49.66220439673356]
  We have created a new dataset, which we call SafetyDetect. The SafetyDetect dataset consists of 1000 anomalous home scenes. Our approach utilizes large language models (LLMs) alongside both a graph representation of the scene and the relationships between the objects in the scene.
  arXiv  Detail & Related papers  (2024-04-12T21:56:21Z)
• Security Advice for Parents and Children About Content Filtering and Circumvention as Found on YouTube and TikTok [2.743215038883957]
  We examine the advice available to parents and children regarding content filtering and circumvention as found on YouTube and TikTok. Our results show that of these videos, roughly three-quarters are accurate, with the remaining one-fourth containing factually incorrect advice. We find that videos targeting children are both more likely to be incorrect and actionable than videos targeting parents, leaving children at increased risk of taking harmful action.
  arXiv  Detail & Related papers  (2024-02-05T18:12:33Z)
• Targeted and Troublesome: Tracking and Advertising on Children's Websites [10.066090482189015]
  We measure the prevalence of trackers, fingerprinting scripts, and advertisements on child-directed websites. Our results show that around 90% of child-directed websites embed one or more trackers, and about 27% contain targeted advertisements. Next, we identify improper ads on child-directed websites by developing an ML pipeline that processes both images and text extracted from ads.
  arXiv  Detail & Related papers  (2023-08-09T11:37:39Z)
• Towards Usable Parental Control for Voice Assistants [6.827452316943251]
  We conduct a parent survey to find out what they like and dislike about the current parental control features. We find that parents need more visuals about their children's activity, easier access to security features for their children, and a better user interface.
  arXiv  Detail & Related papers  (2023-03-09T00:26:42Z)
• 'Beach' to 'Bitch': Inadvertent Unsafe Transcription of Kids' Content on YouTube [13.116806430326513]
  Well-known automatic speech recognition (ASR) systems may produce text content highly inappropriate for kids while transcribing YouTube Kids' videos. We release a first-of-its-kind data set of audios for which the existing state-of-the-art ASR systems hallucinate inappropriate content for kids.
  arXiv  Detail & Related papers  (2022-02-17T19:19:09Z)
• StoryBuddy: A Human-AI Collaborative Chatbot for Parent-Child Interactive Storytelling with Flexible Parental Involvement [61.47157418485633]
  We developed StoryBuddy, an AI-enabled system for parents to create interactive storytelling experiences. A user study validated StoryBuddy's usability and suggested design insights for future parent-AI collaboration systems.
  arXiv  Detail & Related papers  (2022-02-13T04:53:28Z)
• Analysis of Longitudinal Changes in Privacy Behavior of Android Applications [79.71330613821037]
  In this paper, we examine the trends in how Android apps have changed over time with respect to privacy. We examine the adoption of HTTPS, whether apps scan the device for other installed apps, the use of permissions for privacy-sensitive data, and the use of unique identifiers. We find that privacy-related behavior has improved with time as apps continue to receive updates, and that the third-party libraries used by apps are responsible for more issues with privacy.
  arXiv  Detail & Related papers  (2021-12-28T16:21:31Z)
• "Money makes the world go around'': Identifying Barriers to Better Privacy in Children's Apps From Developers' Perspectives [28.40988446675355]
  The industry for children's apps is thriving at the cost of children's privacy. These apps routinely disclose children's data to multiple data trackers and ad networks. We used a mixed-methods approach to investigate why this is happening and how developers might change their practices.
  arXiv  Detail & Related papers  (2021-11-29T15:27:55Z)
• Stop Bugging Me! Evading Modern-Day Wiretapping Using Adversarial Perturbations [47.32228513808444]
  Mass surveillance systems for voice over IP (VoIP) conversations pose a great risk to privacy. We present an adversarial-learning-based framework for privacy protection for VoIP conversations.
  arXiv  Detail & Related papers  (2020-10-24T06:56:35Z)
• Mind the GAP: Security & Privacy Risks of Contact Tracing Apps [75.7995398006171]
  Google and Apple have jointly provided an API for exposure notification in order to implement decentralized contract tracing apps using Bluetooth Low Energy. We demonstrate that in real-world scenarios the GAP design is vulnerable to (i) profiling and possibly de-anonymizing persons, and (ii) relay-based wormhole attacks that basically can generate fake contacts.
  arXiv  Detail & Related papers  (2020-06-10T16:05:05Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.