Related papers: Explaining models relating objects and privacy

Explaining the output of a complex system, such as a Recommender System (RS), is becoming of utmost importance for both users and companies. In this paper we explore the idea that personalized explanations can be learned as recommendation…

Crowd management relies on inspection of surveillance video either by operators or by object detection models. These models are large, making it difficult to deploy them on resource constrained edge hardware. Instead, the computations are…

Many critical applications rely on cameras to capture video footage for analytical purposes. This has led to concerns about these cameras accidentally capturing more information than is necessary. In this paper, we propose a deep learning…

Training reliable deep learning models which avoid making overconfident but incorrect predictions is a longstanding challenge. This challenge is further exacerbated when learning has to be differentially private: protection provided to…

We present associative and causal views of differential privacy. Under the associative view, the possibility of dependencies between data points precludes a simple statement of differential privacy's guarantee as conditioning upon a single…

Collaborative filtering is a very useful general technique for exploiting the preference patterns of a group of users to predict the utility of items to a particular user. Previous research has studied several probabilistic graphic models…

With the increasing usage of smartphones, there is a corresponding increase in the phone metadata generated by individuals using these devices. Managing the privacy of personal information on these devices can be a complex task. Recent…

The pixels in an image, and the objects, scenes, and actions that they compose, determine whether an image will be memorable or forgettable. While memorability varies by image, it is largely independent of an individual observer. Observer…

Today's geo-location estimation approaches are able to infer the location of a target image using its visual content alone. These approaches exploit visual matching techniques, applied to a large collection of background images with known…

A number of learning models used in consequential domains, such as to assist in legal, banking, hiring, and healthcare decisions, make use of potentially sensitive users' information to carry out inference. Further, the complete set of…

Online users often post facial images of themselves and other people on online social networks (OSNs) and other Web 2.0 platforms, which can lead to potential privacy leakage of people whose faces are included in such images. There is…

Humans should be able work more effectively with artificial intelligence-based systems when they can predict likely failures and form useful mental models of how the systems work. We conducted a study of human's mental models of artificial…

Privacy personas capture the differences in user segments with respect to one's knowledge, behavioural patterns, level of self-efficacy, and perception of the importance of privacy protection. Modelling these differences is essential for…

In this paper, we consider the problem of estimating a potentially sensitive (individually stigmatizing) statistic on a population. In our model, individuals are concerned about their privacy, and experience some cost as a function of their…

Image generation models are poised to become ubiquitous in a range of applications. These models are often fine-tuned and evaluated using human quality judgments that assume a universal standard, failing to consider the subjectivity of such…

In this work, we propose information laundering, a novel framework for enhancing model privacy. Unlike data privacy that concerns the protection of raw data information, model privacy aims to protect an already-learned model that is to be…

Concerns for the privacy of individuals captured in public imagery have led to privacy-preserving action recognition. Existing approaches often suffer from issues arising through obfuscation being applied globally and a lack of…

The structure of network data enables simple predictive models to leverage local correlations between nodes to high accuracy on tasks such as attribute and link prediction. While this is useful for building better user models, it introduces…

We propose a general statistical inference framework to capture the privacy threat incurred by a user that releases data to a passive but curious adversary, given utility constraints. We show that applying this general framework to the…

Fairness and privacy are two important concerns in social decision-making processes such as resource allocation. We study privacy in the fair allocation of indivisible resources using the well-established framework of differential privacy.…