Severity: Low
How Microsoft defends against indirect prompt injection attacks
🌍 Limbă / Language:
Traducere automată / Automatic translation
Summary The growing adoption of large language models (LLMs) in enterprise workflows has introduced a new class of adversarial techniques: indirect prompt injection. Indirect prompt injection can be used against systems that leverage large language models (LLMs) to process untrusted data. Fundamentally, the risk is that an attacker could provide specially crafted data that the LLM misinterprets as instructions.
📌 Informații despre sursă
Sursă: Microsoft Security
Link original: https://msrc.microsoft.com/blog/2025/07/how-microsoft-defends-against-indirect-prompt-injection-attacks/ ↗
Importat la: 12 October 2025, 09:54
Publicat: 29 July 2025
⚠️ Această știre a fost importată automat din surse oficiale. Pentru informații actualizate, vă rugăm să consultați direct site-ul sursei.
English 
Romanian