A practical guide to LLM/RAG/Agent security covering prompt injection, external content isolation, tool allowlists, approval gates, and boundary-aware defenses.
A defensive guide to data poisoning and backdoors, with a toy digits experiment, poison rate, attack success rate, and training pipeline controls.
A practical guide to model privacy risks: membership inference, surrogate extraction, confidence leakage, output minimization, and query governance.
A practical AI security threat modeling guide using NIST adversarial ML, MITRE ATLAS, and OWASP LLM Top 10 to map assets, risks, evidence, and controls.
A defensive robustness evaluation walkthrough using the FGSM equation and a safe scikit-learn digits toy experiment.
A defensive walkthrough of the mld_chaffing_v2.py Virtual Mirror project: metadata leaks, entropy, distribution distance, confusion matrices, idle-window micro-pulses, and performance trade-offs.
An accessible explanation of the Transformer architecture and its core component: the Self-Attention mechanism.
An introduction to the most fundamental text representation methods in NLP: Bag of Words (BoW) and TF-IDF.
Understand the core concepts of Recurrent Neural Networks (RNN), the role of hidden states, and their application in NLP.
A source-based walkthrough of cifar10_tiny_cnn.c, covering CIFAR-10 binary input, 3×3 convolution, ReLU, max pooling, fully connected logits, softmax, backpropagation, and local commands.
