ManySpace
English Giriş yap Kayıt ol

Yapay ZekâÖnerilenAIML-SEC-006

Prompt Injection

Untrusted text treated as instructions: direct and indirect injection, and why it is hard to eliminate.

Bu konunun henüz Türkçe çevirisi yok, bu yüzden İngilizce gösteriliyor.

Zorluk
3 / 5
Önem
4 / 5
Çalışma süresi
1–2 sa
Çalışma türü
Karma

Neden önemli

The learner can identify an indirect prompt injection in retrieved content and explain why instruction/data separation fails in LLMs.

Bu konuya giden rota

Rota AIML-SEC-006
What Is a Model? Learning from Data Tasks: Regression, Classification, and Beyond Features and Targets Datasets and Splits Classification Framing Linear Regression I: Prediction and Residuals Embeddings Tokens and Tokenization Sampling and Splits Train, Validation, and Test Errors Scores and Logits Loss and Fitting: Squared Error Similarity in Vector Space Distribution Shift Offline Evaluation Multiclass Scores and Softmax Autoregression Objective Functions and Empirical Risk Query, Key, Value Robustness Evaluation Next-Token Prediction Training vs Serving Similarity Scores Adversarial Examples Weighted Aggregation Self-Attention Threat Modeling for ML Systems Context and Conditioning Prompting and In-Context Learning Prompt Injection