Search Results for author:
Found 31 papers, 14 papers with code
Doing not Being: Concrete Language as a Bridge from Language Technology to Ethnically Inclusive Job Ads
This paper makes the case for studying concreteness in language as a bridge that will allow language technology to support the understanding and improvement of ethnic inclusivity in job advertisements.
Truth or Error? Towards systematic analysis of factual errors in abstractive summaries
This paper presents a typology of errors produced by automatic summarization systems.
Exploring Inspiration Sets in a Data Programming Pipeline for Product Moderation
We carry out a case study on the use of data programming to create data to train classifiers used for product moderation on a large e-commerce platform.
Centered Masking for Language-Image Pre-Training
We introduce Gaussian masking for Language-Image Pre-Training (GLIP) a novel, straightforward, and effective technique for masking image patches during pre-training of a vision-language model.
Tabdoor: Backdoor Vulnerabilities in Transformer-based Neural Networks for Tabular Data
Our findings highlight the urgency of addressing such vulnerabilities and provide insights into potential countermeasures for securing DNN models against backdoors in tabular data.
When Machine Learning Models Leak: An Exploration of Synthetic Training Data
The attack assumes that the attacker can query the model to obtain predictions and that the marginal distribution of the data on which the model was trained is publicly available.
Beyond Neural-on-Neural Approaches to Speaker Gender Protection
Currently, the common practice for developing and testing gender protection algorithms is "neural-on-neural", i. e., perturbations are generated and tested with a neural network.
Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression
Perturbative availability poisons (PAPs) add small changes to images to prevent their use for model training.
Generative Poisoning Using Random Discriminators
We introduce ShortcutGen, a new data poisoning attack that generates sample-dependent, error-minimizing perturbations by learning a generator.
Minimizing Mindless Mentions: Recommendation with Minimal Necessary User Reviews
In this position paper, we make the case for applying the idea of minimal necessary data to recommender systems that use user reviews.
Gender In Gender Out: A Closer Look at User Attributes in Context-Aware Recommendation
This paper studies user attributes in light of current concerns in the recommender system community: diversity, coverage, calibration, and data minimization.
The Importance of Image Interpretation: Patterns of Semantic Misclassification in Real-World Adversarial Images
In this paper, we propose that adversarial images should be evaluated based on semantic mismatch, rather than label mismatch, as used in current work.
Regex in a Time of Deep Learning: The Role of an Old Technology in Age Discrimination Detection in Job Advertisements
Deep learning holds great promise for detecting discriminatory language in the public sphere.
Going Grayscale: The Road to Understanding and Improving Unlearnable Examples
Recent work has shown that imperceptible perturbations can be applied to craft unlearnable examples (ULEs), i. e. images whose content cannot be used to improve a classifier during training.
Doing Data Right: How Lessons Learned Working with Conventional Data should Inform the Future of Synthetic Data for Recommender Systems
We present a case that the newly emerging field of synthetic data in the area of recommender systems should prioritize `doing data right'.
On Success and Simplicity: A Second Look at Transferable Targeted Attacks
In particular, we, for the first time, identify that a simple logit loss can yield competitive results with the state of the arts.
Adversarial Image Color Transformations in Explicit Color Filter Space
In particular, our color filter space is explicitly specified so that we are able to provide a systematic analysis of model robustness against adversarial color transformations, from both the attack and defense perspectives.
Partially Synthetic Data for Recommender Systems: Prediction Performance and Preference Hiding
This paper demonstrates the potential of statistical disclosure control for protecting the data used to train recommender systems.
Adversarial Item Promotion: Vulnerabilities at the Core of Top-N Recommenders that Use Images to Address Cold Start
Our experiments evaluate the danger of these attacks when mounted against three representative visually-aware recommender algorithms in a framework that uses images to address cold start.
The Connection between the Text and Images of News Articles: New Insights for Multimedia Analysis
We carry out a manual analysis of 1000 articles containing a keyword related to flooding.
Adversarial Color Enhancement: Generating Unrestricted Adversarial Images by Optimizing a Color Filter
We introduce an approach that enhances images using a color filter in order to create adversarial effects, which fool neural networks into misclassification.
Towards Large yet Imperceptible Adversarial Image Perturbations with Perceptual Color Distance
The success of image perturbations that are designed to fool image classifier is assessed in terms of both adversarial effect and visual imperceptibility.
Remembering Winter Was Coming: Character-Oriented Video Summaries of TV Series
In this paper, we tackle plot modeling by considering the social network of interactions between the characters involved in the narrative: substantial, durable changes in a major character's social environment suggest a new development relevant for the summary.
Who's Afraid of Adversarial Queries? The Impact of Image Modifications on Content-based Image Retrieval
An adversarial query is an image that has been modified to disrupt content-based image retrieval (CBIR) while appearing nearly untouched to the human eye.
From Volcano to Toyshop: Adaptive Discriminative Region Discovery for Scene Recognition
As deep learning approaches to scene recognition emerge, they have continued to leverage discriminative regions at multiple scales, building on practices established by conventional image classification research.
Assessing the impact of machine intelligence on human behaviour: an interdisciplinary endeavour
The workshop gathered an interdisciplinary group of experts to establish the state of the art research in the field and a list of future research challenges to be addressed on the topic of human and machine intelligence, algorithm's potential impact on human cognitive capabilities and decision making, and evaluation and regulation needs.
Investigating the Effect of Music and Lyrics on Spoken-Word Recognition
Music stretches with and without lyrics were sampled from the same song in order to control for factors beyond the presence of lyrics.
Learning Subclass Representations for Visually-varied Image Classification
The novelty of the approach is that subclass representations make use of not only the content of the photos themselves, but also information on the co-occurrence of their tags, which determines membership in both subclasses and top-level classes.
Pairwise Geometric Matching for Large-Scale Object Retrieval
Spatial verification is a key step in boosting the performance of object-based image retrieval.
Exploiting Social Tags for Cross-Domain Collaborative Filtering
A key question to be answered in the context of CDCF is what common characteristics can be deployed to link different domains for effective knowledge transfer.
Creating a Data Collection for Evaluating Rich Speech Retrieval
We describe the development of a test collection for the investigation of speech retrieval beyond identification of relevant content.
