Sahar Abdelnabi
@sahar-abdelnabi.bsky.social
Researcher @ Microsoft | ex. PhD @ CISPA | Neurodivergent 🧠🦋 | AI safety & security | life and peace for all ☮️, permanent ceasefire 🍉
Opinions my own.
Opinions my own.
📢 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
📅 December 2, 2025
📍 Copenhagen
An opportunity to discuss your work with colleagues working on similar problems in LLM safety and security
October 9, 2025 at 2:16 PM
📢 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
📅 December 2, 2025
📍 Copenhagen
An opportunity to discuss your work with colleagues working on similar problems in LLM safety and security
Reposted by Sahar Abdelnabi
(1/n) In our #ICLR2025 paper, we explore a fundamental issue that enables prompt injections: 𝐋𝐋𝐌𝐬’ 𝐢𝐧𝐚𝐛𝐢𝐥𝐢𝐭𝐲 𝐭𝐨 𝐬𝐞𝐩𝐚𝐫𝐚𝐭𝐞 𝐢𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧𝐬 𝐟𝐫𝐨𝐦 𝐝𝐚𝐭𝐚 𝐢𝐧 𝐭𝐡𝐞𝐢𝐫 𝐢𝐧𝐩𝐮𝐭.
✅ Definition of separation
👉 SEP Benchmark
🔍 LLM evals on SEP
✅ Definition of separation
👉 SEP Benchmark
🔍 LLM evals on SEP
March 18, 2025 at 2:47 PM
(1/n) In our #ICLR2025 paper, we explore a fundamental issue that enables prompt injections: 𝐋𝐋𝐌𝐬’ 𝐢𝐧𝐚𝐛𝐢𝐥𝐢𝐭𝐲 𝐭𝐨 𝐬𝐞𝐩𝐚𝐫𝐚𝐭𝐞 𝐢𝐧𝐬𝐭𝐫𝐮𝐜𝐭𝐢𝐨𝐧𝐬 𝐟𝐫𝐨𝐦 𝐝𝐚𝐭𝐚 𝐢𝐧 𝐭𝐡𝐞𝐢𝐫 𝐢𝐧𝐩𝐮𝐭.
✅ Definition of separation
👉 SEP Benchmark
🔍 LLM evals on SEP
✅ Definition of separation
👉 SEP Benchmark
🔍 LLM evals on SEP