@ZhanQiusi1 esittelemme työtämme keskiviikkona klo 11 posterisessiossa ja lauantain TrustNLP-työpajassa (spotlight talk)! Tervehdi, jos näet hänet
Daniel Kang
Daniel Kang13.3.2025
AI agents are increasingly popular (e.g., OpenAI's operator) but can be attacked to harm users! We show that even with defenses, AI agents can still be compromised via indirect prompt injections via "adaptive attacks" in our NAACL 2025 findings paper 🧵 and links below
285