diff --git a/data/LSIR/projects.yaml b/data/LSIR/projects.yaml index 58d8cca..6bc3177 100644 --- a/data/LSIR/projects.yaml +++ b/data/LSIR/projects.yaml @@ -1,69 +1,4 @@ projects: - pribot: - name: PriBot - categories: - - Privacy - - Learning - applications: - - Info - description: Automated analysis of privacy policies - tech_desc: > - Pribot uses an automated framework for privacy policy analysis (Polisis). It enables scalable, dynamic, and multi-dimensional queries - on natural language privacy policies. - code: - type: Private GitHub - contacts: - - name: Rémi Lebret - email: remi.lebret@epfl.ch - tags: - - Natural Language - language: Python, JavaScript - type: Application - url: https://www.epfl.ch/labs/lsir/pribot/ - information: - - type: Paper - title: "Polisis: Automated Analysis and Presentation of Privacy Policies Using Deep Learning" - url: https://infoscience.epfl.ch/record/270808 - notes: - - label: Published at - text: USENIX'18 - url: https://www.usenix.org/conference/usenixsecurity18/presentation/harkous - license: commercial - date_added: 2019-03-18 - date_updated: 2024-02-07 - - privyseal: - name: PrivySeal - categories: - - Privacy - applications: - - Info - description: Privacy assistant for installing third party cloud apps - tech_desc: > - When installing third party apps for cloud services such as Google Drive or DropBox, PrivySeal compares the required permissions to - the ones actually needed, and informs users about the data-driven insights that these apps can make about them (e.g. topics of - interest, activity patterns, etc.). The goal is to make users aware of these facts and discourage them to install over-privileged - apps. - code: - type: Private GitHub - contacts: - - name: Hamza Harkous - email: hamza.harkous@gmail.com - tags: - - Cloud - language: JavaScript, Python - type: Application - information: - - type: Paper - title: "The Curious Case of the PDF Converter that Likes Mozart: Dissecting and Mitigating the Privacy Risk of Personal Cloud Apps" - url: https://infoscience.epfl.ch/record/218003 - notes: - - label: Published at - text: PETS'16 - url: https://petsymposium.org/2016 - date_added: 2019-03-18 - date_updated: 2022-07-06 - ai-data-platform-v1: name: AI Research Aiding Online Children Safety categories: @@ -192,6 +127,7 @@ projects: url: https://www.mediaobservatory.com code: type: Private GitHub + url: https://github.com/mediaobservatory tags: - Natural Language type: Application @@ -232,3 +168,74 @@ projects: type: Library date_added: 2022-07-06 date_updated: 2024-02-12 + + commpass: + name: CommPass + description: > + News article similarity visualization tool + type: "Application" + categories: + - "Learning" + applications: + - "Info" + tags: + - "Adversarial" + - "Machine Learning" + - "Natural Language" + layman_desc: > + This tool visualizes how similar or different news articles about the + same event are from multiple perspectives. It can show if articles + have a positive or negative stance on the topic. This helps users + understand if they are caught in a filter bubble and exposes them to + diverse viewpoints. It also assists journalists in positioning their + articles among others covering the same story. + tech_desc: > + The project aims to visualize semantic similarity and polarity of news + articles covering a given media event. It extends the NewsTeller + platform which processes over 1.5 million news articles per month. + The goal is to provide intuitive visualization tools to explore the + media landscape and enhance the NewsTeller platform. + url: https://www.media-initiative.ch/project/commpass/ + date_added: 2024-03-19 + + # Most common fields: + upgrade_newsroom: + name: Upgrading the Newsroom + description: > + Automated image selection system for news articles + type: "Application" + categories: + - "Learning" + applications: + - "Info" + tags: + - "Adversarial" + - "Machine Learning" + - "Natural Language" + layman_desc: > + It is an automated system that can recommend suitable images to illustrate + news articles by analyzing the text content of the articles. + The system can handle inputs in multiple languages like German and French + by using aligned multilingual word embeddings. + It uses advanced neural network techniques like attention to identify + the most relevant parts of the text for retrieving matching images from a + large database. + tech_desc: > + The system fuses multiple textual sources (caption, body, headline, lead) + from news articles using a hierarchical attention mechanism to retrieve + relevant images. + It utilizes subword embeddings and self-attention to better encode + entities and capture important keywords within texts. + The model is trained on a large-scale multimodal multilingual dataset of + over 500k German and French news article-image pairs in a + weakly-supervised manner. + url: https://modemos.epfl.ch/article + contacts: + - name: Rémi Lebret + email: remi.lebret@epfl.ch + information: + # One or more of: + - type: Paper + title: "Upgrading the Newsroom: An Automated Image Selection System for News Articles" + url: https://arxiv.org/abs/2004.11449 + date_added: 2024-03-19 diff --git a/updates/2024-big-update.md b/updates/2024-big-update.md index 325bb9f..b8b0dbb 100644 --- a/updates/2024-big-update.md +++ b/updates/2024-big-update.md @@ -96,6 +96,19 @@ Linus - Crowdsourcing Benchmark - "You don't have access" - Added github repo to labs.yaml - 2024-02-20 - sent email to Remi + - 03-05 - reply from Remi: + - Pribot/Polisis/PoliCompare/Privyseal are projects from Hamza Harkous, a former Phd student. + I actually met with him last week, those services are now supposed to be maintained by + his partner at the University of Wisconsin. + It looks like they are not doing their jobs :) Anyway, those services are quite old now. + It is OK to remove them from your portofolio. + - TinyGSN/ArgSM/Crowdsourcing Benchmark —> I don’t know about these projects. + They are even older I guess. You can remove those. + - Infoscience —> les papiers qui sont déjà en open-access ne sont généralement pas sur infoscience, + is that bad? + - media-observatory —> repo is public: https://github.com/mediaobservatory + - For the active projects, we are maintaining the list here: https://modemos.epfl.ch/ + - 03-19 - answered to Rémi - NAL - Katerina Argyraki - On lab page https://www.epfl.ch/labs/nal/ - failing link to https://vigor.epfl.ch/ in `first framework for verifying software NFs with no verification expertise`