<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>News on Damien Riquet</title><link>https://driquet.info/news/</link><description>Recent content in News on Damien Riquet</description><generator>Hugo -- gohugo.io</generator><language>en</language><copyright>© 2023–2026 Damien Riquet · CC BY 4.0</copyright><atom:link href="https://driquet.info/news/index.xml" rel="self" type="application/rss+xml"/><item><title>A New Look, and a Newsletter</title><link>https://driquet.info/news/new-site-and-newsletter/</link><pubDate>Sun, 22 Nov 2026 10:00:00 +0100</pubDate><guid>https://driquet.info/news/new-site-and-newsletter/</guid><description>The site got a redesign: a simpler homepage, a News section, tag filters, and a newsletter to get new posts by email.</description></item><item><title>Dr. Gabriel Loiseau: PhD Defended!</title><link>https://driquet.info/news/gabriel-loiseau-phd/</link><pubDate>Mon, 02 Nov 2026 18:00:00 +0100</pubDate><guid>https://driquet.info/news/gabriel-loiseau-phd/</guid><description>Gabriel Loiseau defended his PhD on privacy- and utility-preserving text anonymization. A look back at his thesis, his papers, and what comes next.</description></item><item><title>M3AAWG 68th General Meeting in Paris</title><link>https://driquet.info/news/m3aawg-68-paris/</link><pubDate>Thu, 29 Oct 2026 18:00:00 +0100</pubDate><guid>https://driquet.info/news/m3aawg-68-paris/</guid><description>At the M3AAWG 68th General Meeting in Paris, Gabriel Loiseau and I gave a training on getting better results from LLMs without fine-tuning and without wasting tokens.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://driquet.info/news/m3aawg-68-paris/featured.webp"/></item><item><title>New Role: AI SIG Leader at M3AAWG</title><link>https://driquet.info/news/m3aawg-ai-sig/</link><pubDate>Fri, 09 Oct 2026 08:00:00 +0200</pubDate><guid>https://driquet.info/news/m3aawg-ai-sig/</guid><description>Since early 2026, I lead the Artificial Intelligence Special Interest Group at M3AAWG, the anti-abuse industry's working group.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://driquet.info/news/m3aawg-ai-sig/featured.webp"/></item><item><title>My PhD Students Rock: Three New Publications</title><link>https://driquet.info/news/my-phd-students-rock/</link><pubDate>Tue, 30 Jun 2026 08:00:00 +0200</pubDate><guid>https://driquet.info/news/my-phd-students-rock/</guid><description>Three new papers from my PhD students, on text anonymization, privacy assessment, and intent detection in phishing emails.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://driquet.info/news/my-phd-students-rock/featured.webp"/></item><item><title>LREC 2026 with Gabriel and Senaid</title><link>https://driquet.info/news/lrec-2026/</link><pubDate>Sat, 16 May 2026 18:00:00 +0200</pubDate><guid>https://driquet.info/news/lrec-2026/</guid><description>At LREC 2026 in Palma, Senaid presented DIDECO, our dataset for intent detection in digital communications, and Gabriel presented our work on distilling privacy assessment.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://driquet.info/news/lrec-2026/featured.webp"/></item><item><title>M3AAWG 66th General Meeting in San Diego</title><link>https://driquet.info/news/m3aawg-66-san-diego/</link><pubDate>Thu, 19 Feb 2026 18:00:00 -0800</pubDate><guid>https://driquet.info/news/m3aawg-66-san-diego/</guid><description>At the M3AAWG 66th General Meeting in San Diego, I gave a hands-on training on how AI agents get exploited, and the defenses that hold up.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://driquet.info/news/m3aawg-66-san-diego/featured.webp"/></item><item><title>Tau-Eval: A Unified Evaluation Framework for Useful and Private Text Anonymization</title><link>https://driquet.info/news/taueval/</link><pubDate>Wed, 15 Oct 2025 08:00:00 +0100</pubDate><guid>https://driquet.info/news/taueval/</guid><description>Tau-Eval, accepted at the EMNLP 2025 Demo Track: an open-source framework to evaluate text anonymization on both privacy and utility.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://driquet.info/news/taueval/featured.webp"/></item><item><title>Detection of Cyberthreats with Computer Vision (Part 3)</title><link>https://driquet.info/cyberthreats-computer-vision-part-three/</link><pubDate>Fri, 13 Jun 2025 10:40:45 +0200</pubDate><guid>https://driquet.info/cyberthreats-computer-vision-part-three/</guid><description>Part 3 of my Hornetsecurity series on image analysis: content-based near-duplicate detection, such as object recognition and embedded text.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://driquet.info/cyberthreats-computer-vision-part-three/featured.png"/></item><item><title>M3AAWG 64th General Meeting in Vancouver</title><link>https://driquet.info/news/m3aawg-64-vancouver/</link><pubDate>Thu, 05 Jun 2025 18:00:00 -0700</pubDate><guid>https://driquet.info/news/m3aawg-64-vancouver/</guid><description>At the M3AAWG 64th General Meeting in Vancouver, my first one on site, I gave a talk on how LLMs can leak sensitive information, and how to defend against it.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://driquet.info/news/m3aawg-64-vancouver/featured.webp"/></item><item><title>TAROT: Task-Oriented Authorship Obfuscation Using Policy Optimization Methods</title><link>https://driquet.info/news/tarot/</link><pubDate>Fri, 21 Mar 2025 09:02:08 +0100</pubDate><guid>https://driquet.info/news/tarot/</guid><description>TAROT, accepted at PrivateNLP 2025: rewriting text with small policy-optimized models to hide its author while keeping it useful.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://driquet.info/news/tarot/featured.webp"/></item><item><title>Detection of Cyberthreats with Computer Vision (Part 2)</title><link>https://driquet.info/cyberthreats-computer-vision-part-two/</link><pubDate>Wed, 26 Feb 2025 01:00:00 +0100</pubDate><guid>https://driquet.info/cyberthreats-computer-vision-part-two/</guid><description>Part 2 of my Hornetsecurity series on image analysis: spotting duplicate and near-duplicate phishing images with hashes and color histograms.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://driquet.info/cyberthreats-computer-vision-part-two/featured.webp"/></item><item><title>WikiPhish: A Diverse Wikipedia-Based Dataset for Phishing Website Detection</title><link>https://driquet.info/news/wikiphish/</link><pubDate>Tue, 09 Apr 2024 11:21:45 +0200</pubDate><guid>https://driquet.info/news/wikiphish/</guid><description>WikiPhish, accepted at CODASPY 2024: a phishing website dataset of 110,606 pages, with Wikipedia as a diverse source of legitimate ones.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://driquet.info/news/wikiphish/featured.jpg"/></item><item><title>Targeted Attacks: Redefining Spear Phishing and Business Email Compromise</title><link>https://driquet.info/news/targeted-attacks-arxiv/</link><pubDate>Sat, 30 Sep 2023 15:27:15 +0200</pubDate><guid>https://driquet.info/news/targeted-attacks-arxiv/</guid><description>Our arXiv preprint proposes one definition of targeted attacks, covering spear phishing and Business Email Compromise, and reviews how to detect them.</description><media:content xmlns:media="http://search.yahoo.com/mrss/" url="https://driquet.info/news/targeted-attacks-arxiv/featured.jpg"/></item></channel></rss>