Distributed machine learning is primarily motivated by the promise of increased computation power for accelerating training and mitigating privacy concerns. Unlike machine learning on a single device, distributed machine learning requires collaboration and communication among the devices. This creates several new challenges: (1) the heavy communication overhead can be a bottleneck that slows down the training, and (2) the unreliable communication and weaker control over the remote entities make the distributed system vulnerable to systematic failures and malicious attacks. This paper presents a variant of stochastic gradient descent (SGD) with improved communication efficiency and security in distributed environments. Our contributions include (1) a new technique called error reset to adapt both infrequent synchronization and message compression for communication reduction in both synchronous and asynchronous training, (2) new score-based approaches for validating the updates, and (3) integration with both error reset and score-based validation. The proposed system provides communication reduction, both synchronous and asynchronous training, Byzantine tolerance, and local privacy preservation. We evaluate our techniques both theoretically and empirically.
more »
« less
Failure Explanation in Privacy-Sensitive Contexts: An Integrated Systems Approach
In this paper, we explore how robots can properly
explain failures during navigation tasks with privacy concerns.
We present an integrated robotics approach to generate visual
failure explanations, by combining a language-capable cognitive
architecture (for recognizing intent behind commands), an
object- and location-based context recognition system (for
identifying the locations of people and classifying the context in
which those people are situated) and an infeasibility proof-based
motion planner (for explaining planning failures on the basis of
contextually mediated privacy concerns). The behavior of this
integrated system is validated using a series of experiments in
a simulated medical environment.
more »
« less
- Award ID(s):
- 1849348
- NSF-PAR ID:
- 10458324
- Date Published:
- Journal Name:
- IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The increased adoption of smart home cameras (SHCs) foregrounds issues of surveillance, power, and privacy in homes and neighborhoods. However, questions remain about how people are currently using these devices to monitor and surveil, what the benefits and limitations are for users, and what privacy and security tensions arise between primary users and other stakeholders. We present an empirical study with 14 SHC users to understand how these devices are used and integrated within everyday life. Based on semistructured qualitative interviews, we investigate users’ motivations, practices, privacy concerns, and social negotiations. Our findings highlight the SHC as a perceptually powerful and spatially sensitive device that enables a variety of surveillant uses outside of basic home security—from formally surveilling domestic workers, to casually spying on neighbors, to capturing memories. We categorize surveillant SHC uses, clarify distinctions between primary and non primary users, and highlight under-considered design directions for addressing power imbalances among primary and non-primary users.more » « less
-
Monitoring the compliance of social distancing is critical for schools and offices to recover in-person operations in indoor spaces from the COVID-19 pandemic. Existing systems focus on vision- and wearable-based sensing approaches, which require direct line-of-sight or device-carrying and may also raise privacy concerns. To overcome these limitations, we introduce a new monitoring system for social distancing compliance based on footstep-induced floor vibration sensing. This system is device-free, non-intrusive, and perceived as more privacy-friendly. Our system leverages the insight that footsteps closer to the sensors generate vibration signals with larger amplitudes. The system first estimates the location of each person relative to the sensors based on signal energy and then infers the distance between two people. We evaluated the system through a real-world experiment with 8 people, and the system achieves an average accuracy of 97.8% for walking scenario classification and 80.4% in social distancing violation detection.more » « less
-
null (Ed.)This paper examines people’s privacy concerns, perceptions of social benefits, and acceptance of various COVID-19 control measures that harness location information using data collected through an online survey in the U.S. and South Korea. The results indicate that people have higher privacy concerns for methods that use more sensitive and private information. The results also reveal that people’s perceptions of social benefits are low when their privacy concerns are high, indicating a trade-off relationship between privacy concerns and perceived social benefits. Moreover, the acceptance by South Koreans for most mitigation methods is significantly higher than that by people in the U.S. Lastly, the regression results indicate that South Koreans (compared to people in the U.S.) and people with a stronger collectivist orientation tend to have higher acceptance for the control measures because they have lower privacy concerns and perceive greater social benefits for the measures. These findings advance our understanding of the important role of geographic context and culture as well as people’s experiences of the mitigation measures applied to control a previous pandemic.more » « less
-
more » « less
Smart voice assistants such as Amazon Alexa and Google Home are becoming increasingly pervasive in our everyday environments. Despite their benefits, their miniaturized and embedded cameras and microphones raise important privacy concerns related to surveillance and eavesdropping. Recent work on the privacy concerns of people in the vicinity of these devices has highlighted the need for 'tangible privacy', where control and feedback mechanisms can provide a more assured sense of whether the camera or microphone is 'on' or 'off'. However, current designs of these devices lack adequate mechanisms to provide such assurances. To address this gap in the design of smart voice assistants, especially in the case of disabling microphones, we evaluate several designs that incorporate (or not) tangible control and feedback mechanisms. By comparing people's perceptions of risk, trust, reliability, usability, and control for these designs in a between-subjects online experiment (N=261), we find that devices with tangible built-in physical controls are perceived as more trustworthy and usable than those with non-tangible mechanisms. Our findings present an approach for tangible, assured privacy especially in the context of embedded microphones.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
