ASIDE accepted to #ICLR2026! 🇧🇷🎉
We architecturally separate instructions and data in LLMs by rotating data token embeddings 90° during the forward pass: one extra matmul, virtually no overhead.
Models & code open-sourced ⬇️
✨ 𝗦𝘂𝗯𝗺𝗶𝘀𝘀𝗶𝗼𝗻 𝗜𝗻𝗳𝗼:
- Quick application
- Accepting posters for 2025 papers from top ML / Security venues
- 𝗗𝗲𝗮𝗱𝗹𝗶𝗻𝗲: October 28, 2025
- Notifications: October 31, 2025
Submission link: docs.google.com/forms/d/e/1F...
Workshop website: llmsafety-unconference.github.io
📢 𝗖𝗮𝗹𝗹 𝗳𝗼𝗿 𝗣𝗼𝘀𝘁𝗲𝗿𝘀: 𝗟𝗟𝗠 𝗦𝗮𝗳𝗲𝘁𝘆 𝗮𝗻𝗱 𝗦𝗲𝗰𝘂𝗿𝗶𝘁𝘆 𝗪𝗼𝗿𝗸𝘀𝗵𝗼𝗽 @ 𝗘𝗟𝗟𝗜𝗦 𝗨𝗻𝗖𝗼𝗻𝗳𝗲𝗿𝗲𝗻𝗰𝗲
📅 December 2, 2025
📍 Copenhagen
An opportunity to discuss your work with colleagues working on similar problems in LLM safety and security
Flying to #ICLR2026 🇧🇷 to present our paper, ASIDE: a parameter-free 90° rotation of data embeddings gives LLMs built-in instruction-data separation, cutting prompt injection rates without explicit safety training.
📍Thu Apr 23, 10:30, Pavilion 4, #3910
⬇️ Paper, Code, Models
Results: much higher instruction-data separation, stronger prompt injection robustness, no utility loss. Also, near-perfect linear separability on instructions vs data at every layer of the model.
Thanking my collaborators:
Evgenii Kortukov, @kotekjedi.bsky.social , Alexandra Volkova, Soroush Tabesh, Sebastian Lapuschkin, Wojciech Samek, @mlcv-at-ista.bsky.social
We’re hosting a poster session at the LLM Safety and Security Workshop (ELLIS UnConference) on December 2, 2025 in Copenhagen, Denmark. We invite attendees to present already published 2025 work in areas related to LLM safety and security. Eligibility. Posters must be based on papers accepted in 2025 at a top venue (or an associated LLM safety/security workshop). If your venue isn’t listed, please enter it manually. First-author or any co-author may present. Selection policy. We aim to accept as many posters as our space allows. If submissions exceed capacity, earlier submissions will be prioritized (first-come, first-served). Deadlines. Submission deadline: October 28, 2025 Notification: October 31, 2025
In colab with Evgenii Kortukov,
@kotekjedi.bsky.social , Alexandra Volkova, Soroush Tabesh, Sebastian Lapuschkin, Wojciech Samek,
@mlcv-at-ista.bsky.social
🎉 Excited to announce the Workshop on Foundations of LLM Security at #EurIPS2025!
🇩🇰 Dec 6–7, Copenhagen!
📢 Call for contributed talks is now open! See details at llmsec-eurips.github.io
#EurIPS @euripsconf.bsky.social @sahar-abdelnabi.bsky.social @aideenfay.bsky.social @thegruel.bsky.social
