2.8k citations
- Max Planck SocietyDE261 papers
- Saarland UniversityDE124 papers
- Technische Universität BerlinDE55 papers
- Centre National de la Recherche ScientifiqueFR41 papers
- Korea UniversityKR41 papers
- Stanford UniversityUS25 papers
- Institut national de recherche en sciences et technologies du numériqueFR24 papers
- ETH ZurichCH21 papers
- Helmholtz Center for Information SecurityDE20 papers
- Technical University of MunichDE20 papers
- Université de LorraineFR17 papers
- University of LuxembourgLU16 papers
6 papers · 2 filters
Fooling Vision and Language Models Despite Localization and Attention Mechanism
Xiaojun Xu, Xinyun Chen, Chang Liu +3
Adversarial attacks are known to succeed on classifiers, but it has been an open question whether more complex vision systems are vulnerable. In this paper, we study adversarial ex…
People on Media: Jointly Identifying Credible News and Trustworthy Citizen Journalists in Online Communities
Subhabrata Mukherjee, Gerhard Weikum
Media seems to have become more partisan, often providing a biased coverage of news catering to the interest of specific groups. It is therefore essential to identify credible info…
People on Drugs: Credibility of User Statements in Health Communities
Subhabrata Mukherjee, Gerhard Weikum, Cristian Danescu-Niculescu-Mizil
Online health communities are a valuable source of information for patients and physicians. However, such user-generated resources are often plagued by inaccuracies and misinformat…
Item Recommendation with Evolving User Preferences and Experience
Subhabrata Mukherjee, Hemank Lamba, Gerhard Weikum
Current recommender systems exploit user and item similarities by collaborative filtering. Some advanced methods also consider the temporal evolution of item ratings as a global ba…
Item Recommendation with Continuous Experience Evolution of Users using Brownian Motion
Subhabrata Mukherjee, Stephan Guennemann, Gerhard Weikum
Online review communities are dynamic as users join and leave, adopt new vocabulary, and adapt to evolving trends. Recent work has shown that recommender systems benefit from expli…
Identifying Consistent Statements about Numerical Data with Dispersion-Corrected Subgroup Discovery
Mario Boley, Bryan R. Goldsmith, Luca M. Ghiringhelli +1
Existing algorithms for subgroup discovery with numerical targets do not optimize the error or target variable dispersion of the groups they find. This often leads to unreliable or…