{"id":25,"date":"2024-06-03T22:59:58","date_gmt":"2024-06-03T20:59:58","guid":{"rendered":"https:\/\/essai-conference.eu\/?page_id=25"},"modified":"2026-09-03T14:11:51","modified_gmt":"2026-09-03T12:11:51","slug":"program","status":"publish","type":"page","link":"https:\/\/essai-conference.eu\/index.php\/program\/","title":{"rendered":"Program"},"content":{"rendered":"\n
\"\"<\/span>
\n

PROGRAM<\/p>\n<\/div><\/div>\n\n\n\n

<\/p>\n\n\n\n

Session #1: Agentic AI and Cybersecurity<\/h2>\n\n\n\n

Thursday, November 19th \u2013 9:00-12:00 \u2013 Room La Nef<\/p>\n\n\n\n

\n
\n

09:00 – 09:30<\/p>\n<\/div>\n\n\n\n

\n

From Cyber Warfare to AI Warfare: The Path Ahead
Vincent Lenders<\/strong>
ELSA \u2013 European Lighthouse on Secure and Safe AI<\/a><\/span> 2026<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n
\n

09:30 – 10:00<\/p>\n<\/div>\n\n\n\n

\n

LLMs as Hackers: Autonomous Linux Privilege Escalation Attacks<\/a>
Andreas Happe, Aaron Kaplan<\/strong>, J\u00fcrgen Cito
Empirical Software Engineering <\/a>2026
<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n
\n

10:00 – 10:30<\/p>\n<\/div>\n\n\n\n

\n

BAXBENCH: Can LLMs Generate Correct and Secure Backends<\/a>
Mark Vero<\/strong>, Niels M\u00fcndler, Victor Chibotaru, Veselin Raychev, Maximilian Baader, Nikola Jovanovi\u0107, Jingxuan He, Martin Vechev
https:\/\/baxbench.com\/<\/a>
ICML<\/a> 2025<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n
\n

10:30 – 11:00<\/p>\n<\/div>\n\n\n\n

\n

Break<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n
\n

11:00 – 11:30<\/p>\n<\/div>\n\n\n\n

\n

LLM-CVX: A Benchmarking Framework for Assessing the Offensive Potential of LLMs in Exploiting CVEs<\/a>
Mohamed Amine El Yagouby, Abdelkader Lahmadi,<\/strong> Mehdi Zakroum, Olivier Festor, Mounir Ghogho
AISec<\/a> 2025
<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n
\n

11:30 – 12:00<\/p>\n<\/div>\n\n\n\n

\n

TBD<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n\n\n\n

Session #2: AI Security<\/h2>\n\n\n\n

Thursday, November 19th – 13:30-18:00 \u2013 Room La Nef<\/p>\n\n\n\n

\n
\n

13:30 – 14:00<\/p>\n<\/div>\n\n\n\n

\n

Fewer Weights, More Problems: A Practical Attack on LLM Pruning<\/a>
Kazuki Egashira,<\/strong> Robin Staab, Thibaud Gloaguen, Mark Vero, Martin Vechev
ICLR<\/a> 2026
<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n
\n

14:00 – 14:30<\/p>\n<\/div>\n\n\n\n

\n

Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols<\/a>
Mikhail Terekhov, Alexander Panfilov,<\/strong> Daniil Dzenhaliou, Caglar Gulcehre, Maksym Andriushchenko, Ameya Prabhu, Jonas Geiping
ICLR<\/a> 2026<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n
\n

14:30 – 15:00<\/p>\n<\/div>\n\n\n\n

\n

SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)<\/a>
Matthieu Meeus, Igor<\/strong> Shilov<\/strong>, Shubham Jain, Manuel Faysse, Marek Rei, Yves-Alexandre de Montjoye
ICLR<\/a> 2026<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n
\n

15:00 – 15:30<\/p>\n<\/div>\n\n\n\n

\n

Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning<\/a>
Wassim Bouaziz<\/strong>, Mathurin Videau, Nicolas Usunier, El-Mahdi El-Mhamdi
ICLR<\/a> 2026<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n
\n

15:30 – 16:00<\/p>\n<\/div>\n\n\n\n

\n

Break<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n
\n

16:00 – 16:30<\/p>\n<\/div>\n\n\n\n

\n

Optimizing Agent Planning for Security and Autonomy<\/a><\/em>
Aashish Kolluri, Rishi<\/strong> Sharma<\/strong>, Manuel Costa, Boris K\u00f6pf, Tobias Nie\u00dfen, Mark Russinovich, Shruti Tople, Santiago Zanella-B\u00e9guelin
ICLR<\/a> 2026<\/p>\n<\/div>\n<\/div>\n\n\n\n

\n
\n

16:30 – 17:00<\/p>\n<\/div>\n\n\n\n

\n

On the Robustness of Tabular Foundation Models: Test-Time Attacks and In-Context Defenses<\/a><\/em>
Mohamed Djilani, Thibault Simonetto, Karim<\/strong> Tit<\/strong>, Florian Tambon, Salah Ghamizi, Maxime Cordy, Mike Papadakis
SaTML<\/a> 2026
<\/p>\n<\/div>\n<\/div>\n\n\n\n

<\/p>\n","protected":false},"excerpt":{"rendered":"

Session #1: Agentic AI and Cybersecurity Thursday, November 19th \u2013 9:00-12:00 \u2013 Room La Nef 09:00 – 09:30 From Cyber Warfare to AI Warfare: The Path Ahead Vincent LendersELSA \u2013 European Lighthouse on Secure and Safe AI 2026 09:30 – 10:00 LLMs as Hackers: Autonomous Linux Privilege Escalation AttacksAndreas Happe, Aaron Kaplan, J\u00fcrgen CitoEmpirical Software … <\/p>\n

Lire la suite de\u00ab\u00a0Program\u00a0\u00bb<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-25","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/essai-conference.eu\/index.php\/wp-json\/wp\/v2\/pages\/25","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/essai-conference.eu\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/essai-conference.eu\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/essai-conference.eu\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/essai-conference.eu\/index.php\/wp-json\/wp\/v2\/comments?post=25"}],"version-history":[{"count":78,"href":"https:\/\/essai-conference.eu\/index.php\/wp-json\/wp\/v2\/pages\/25\/revisions"}],"predecessor-version":[{"id":385,"href":"https:\/\/essai-conference.eu\/index.php\/wp-json\/wp\/v2\/pages\/25\/revisions\/385"}],"wp:attachment":[{"href":"https:\/\/essai-conference.eu\/index.php\/wp-json\/wp\/v2\/media?parent=25"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}