(1/n) In our #ICLR2025 paper, we explore a fundamental issue that enables prompt injections: ๐๐๐๐ฌโ ๐ข๐ง๐๐๐ข๐ฅ๐ข๐ญ๐ฒ ๐ญ๐จ ๐ฌ๐๐ฉ๐๐ซ๐๐ญ๐ ๐ข๐ง๐ฌ๐ญ๐ซ๐ฎ๐๐ญ๐ข๐จ๐ง๐ฌ ๐๐ซ๐จ๐ฆ ๐๐๐ญ๐ ๐ข๐ง ๐ญ๐ก๐๐ข๐ซ ๐ข๐ง๐ฉ๐ฎ๐ญ.
โ Definition of separation
๐ SEP Benchmark
๐ LLM evals on SEP
Egor Zverev
We're hosting a poster session at the UnConference
๐ ๐ช๐ต๐ ๐ฃ๐ฟ๐ฒ๐๐ฒ๐ป๐?
- Connect with researchers working on LLM Safety and Security
- Share insights from your recently published research
- Get feedback and fresh perspectives
- Find new collaborators among participants
๐ข ๐๐ฎ๐น๐น ๐ณ๐ผ๐ฟ ๐ฃ๐ผ๐๐๐ฒ๐ฟ๐: ๐๐๐ ๐ฆ๐ฎ๐ณ๐ฒ๐๐ ๐ฎ๐ป๐ฑ ๐ฆ๐ฒ๐ฐ๐๐ฟ๐ถ๐๐ ๐ช๐ผ๐ฟ๐ธ๐๐ต๐ผ๐ฝ @ ๐๐๐๐๐ฆ ๐จ๐ป๐๐ผ๐ป๐ณ๐ฒ๐ฟ๐ฒ๐ป๐ฐ๐ฒ
๐ December 2, 2025
๐ Copenhagen
An opportunity to discuss your work with colleagues working on similar problems in LLM safety and security
โจ ๐ฆ๐๐ฏ๐บ๐ถ๐๐๐ถ๐ผ๐ป ๐๐ป๐ณ๐ผ:
- Quick application
- Accepting posters for 2025 papers from top ML / Security venues
- ๐๐ฒ๐ฎ๐ฑ๐น๐ถ๐ป๐ฒ: October 28, 2025
- Notifications: October 31, 2025
Submission link: docs.google.com/forms/d/e/1F...
Workshop website: llmsafety-unconference.github.io
๐ ๏ธ ๐ข๐ฟ๐ด๐ฎ๐ป๐ถ๐๐ฒ๐ฟ๐: @egorzverev.bsky.social, @aideenfay.bsky.social, myself, Mario Fritz, @thegruel.bsky.social
Looking forward to interesting discussions in Copenhagen!
#EurIPS2025 #LLMSafety #LLMSecurity #AIResearch #ELLIS #AISafety #EurIPS
