Adversarial Examples and Robust Evaluation: From FGSM to a scikit-learn Digits Experiment
AI Learning Project
Adversarial Examples and Robust Evaluation: From FGSM to a scikit-learn Digits Experiment
A defensive robustness evaluation walkthrough using the FGSM equation and a safe scikit-learn digits toy experiment.
AI Learning Project

Adversarial Examples and Robust Evaluation: From FGSM to a scikit-learn Digits Experiment

Reading info

Level: Professional Reading time: 11 min
  • Adversarial Examples
  • FGSM
  • Robust Evaluation
  • scikit-learn
Open knowledge map

Adversarial examples are not just random noise. In ML security, they are inputs designed around an objective so that small perturbations change model behavior. A professional evaluation should report more than clean accuracy: it needs perturbed accuracy, confidence shifts, failure cases, and defense cost.

This article starts from the FGSM equation and uses the scikit-learn digits dataset for a local safety-bounded experiment. The demo targets only a local toy model. It does not access the network or interact with any real service.

1. Threat model

An adversarial evaluation should state at least four boundaries:

  • Attacker knowledge: white-box parameters or black-box prediction queries.
  • Perturbation budget: how much the input may change, such as an L-infinity epsilon.
  • Attack goal: any wrong class or a specific target class.
  • Evaluation target: model only, preprocessing pipeline, abstention policy, or full product system.

Without these conditions, the word “robust” is not comparable.

2. The FGSM intuition

FGSM uses the gradient of loss with respect to the input. A common form is:

x_adv = clip(x + epsilon * sign(grad_x J(theta, x, y)))

J is the loss, theta is the model parameter set, x is the input, and y is the true label. The perturbation moves the input in the direction that increases loss fastest under the chosen budget. If the decision boundary is close, a small movement can change the prediction.

3. Local digits experiment

The lab script trains a multinomial logistic regression model and computes an input-gradient perturbation from the learned weights. Run:

cd ai-security-lab
python src/fgsm_digits_demo.py --quick --out results/fgsm-results.csv

The output CSV contains epsilon, clean_accuracy, perturbed_accuracy, and accuracy_drop. The useful signal is not one score. It is the curve showing how perturbed accuracy changes as epsilon increases.

4. What robust evaluation should report

  • Clean accuracy and perturbed accuracy.
  • A list of perturbation budgets, not one epsilon.
  • Input constraints such as clipping to valid pixel range.
  • Failure distribution by class, not just the mean.
  • Latency, abstention rate, and false positive cost after defenses.

A claim that accuracy improved after a defense is hard to cite unless the attack budget, evaluation set, and failure handling are clear.

5. Engineering controls

  • Add robustness testing to model release gates.
  • Use calibrated confidence and abstention for high-risk inputs.
  • Log model version, data version, and attack parameters.
  • Do not treat robustness on one benchmark as cross-distribution safety.
  • Add human review and anomaly monitoring at the product layer.

6. Limitations

FGSM is a clear one-step teaching attack, not the strongest possible attack. A full robustness program should also consider PGD, AutoAttack, natural distribution shift, and physical-world transformations. This demo explains evaluation mechanics; it does not prove system safety.

7. References

Internal links

Related tutorials

Review foundation AI Security Threat Modeling

Build a defense map with NIST adversarial ML, MITRE ATLAS, and OWASP LLM risks.

 Continue next Data Poisoning and Backdoor Defense

Study poison rate, trigger behavior, attack success rate, and training pipeline controls.

 Learning path AI Learning Path

Read AI foundations, machine learning, CNN work, traffic defense, and AI security in order.

 Resources Resource Library

Download companion code, datasets, diagrams, model files, and notes.

 Topic hub Student AI Projects

Connect handwritten digits, browser demos, and CNN projects into a portfolio path.

Search questions

FAQ

Who is this article for?

This article is for readers who want a professional-level guide to Adversarial Examples and Robust Evaluation. It takes about 11 min and focuses on Adversarial Examples, FGSM, Robust Evaluation, scikit-learn.

What should I read next?

The recommended next step is Data Poisoning and Backdoor Defense, so the article connects into a longer learning route instead of ending as an isolated note.

Does this article include runnable code or companion resources?

Yes. Use the run notes, resource cards, and download links on the page to reproduce the example or inspect the companion files.

How does this article fit into the larger site?

It is connected to the article context block, learning routes, resources, and project timeline so readers can move from concept to implementation.

Article context

AI Learning Project

A practical route from AI concepts to machine learning workflow, evaluation, neural networks, Python practice, handwritten digits, a CIFAR-10 CNN, adversarial traffic-defense notes, and AI security.

Level: Professional Reading time: 11 min
  • Adversarial Examples
  • FGSM
  • Robust Evaluation
  • scikit-learn

Your next step

Continue: Data Poisoning and Backdoor Defense
Open resource View project
Other language version 对抗样本与鲁棒评估：从 FGSM 公式到 scikit-learn 数字分类实验
Share summary Adversarial Examples and Robust Evaluation

Evaluate clean and perturbed accuracy with an FGSM-style digits experiment.

Download share card Open share center

Companion resources

Leave a Reply

Project timeline

Published posts

  1. AI Basics Learning Roadmap Separate AI, machine learning, and deep learning before going into implementation details.
  2. Machine Learning Workflow Follow the practical path from data and features to training, prediction, and evaluation.
  3. Model Training and Evaluation Understand loss, overfitting, train/test splits, accuracy, recall, and F1.
  4. Neural Network Basics Move from perceptrons to activation, forward propagation, backpropagation, and training loops.
  5. NLP Basics: Understanding Bag of Words and TF-IDF An introduction to the most fundamental text representation methods in NLP: Bag of Words (BoW) and TF-IDF.
  6. RNN Basics: Handling Sequential Data with Memory Understand the core concepts of Recurrent Neural Networks (RNN), the role of hidden states, and their application in NLP.
  7. Transformer Self-Attention Read Q/K/V, scaled dot-product attention, multi-head attention, and positional encoding before exploring LLM internals.
  8. Python AI Mini Practice Run a small scikit-learn classification task and read the experiment output.
  9. Handwritten Digit Dataset Basics Read train.csv, test.csv, labels, and the flattened 28 by 28 pixel layout before training the classifier.
  10. Handwritten Digit Softmax in C Follow the C implementation from logits and softmax probabilities to confusion matrices and submission export.
  11. Handwritten Digit Playground Notes See how the offline classifier was adapted into a browser demo with drawing input and probability output.
  12. CIFAR-10 Tiny CNN Tutorial in C Build and train a small convolutional neural network for CIFAR-10 image classification, then read its loss and accuracy output.
  13. Building a Tiny CIFAR-10 CNN in C: Convolution, Pooling, and Backpropagation A source-based walkthrough of cifar10_tiny_cnn.c, covering CIFAR-10 binary input, 3x3 convolution, ReLU, max pooling, fully connected logits, softmax, backpropagation, and local commands.
  14. High-Entropy Traffic Defense Notes Study encrypted metadata leaks, entropy, traffic classifiers, and a defensive Python chaffing prototype.
  15. AI Security Threat Modeling Build a defense map with NIST adversarial ML, MITRE ATLAS, and OWASP LLM risks.
  16. Adversarial Examples and Robust Evaluation Evaluate clean and perturbed accuracy with an FGSM-style digits experiment.
  17. Data Poisoning and Backdoor Defense Study poison rate, trigger behavior, attack success rate, and training pipeline controls.
  18. Model Privacy and Extraction Defense Measure membership inference signal and surrogate fidelity against a local toy model.
  19. LLM, RAG, and Agent Security Separate instructions from data and enforce tool permissions against indirect prompt injection.

Published resources

  1. Python AI practice code guide The article includes a runnable scikit-learn classification script.
  2. digit_softmax_classifier.c The C source for the handwritten digit softmax classifier.
  3. train.csv.zip Compressed handwritten digit training set with 42000 labeled samples.
  4. test.csv.zip Compressed handwritten digit test set with 28000 unlabeled samples.
  5. sample_submission.csv The official submission format example for checking the final output columns.
  6. submission.csv The prediction file generated by the current C project.
  7. digit-playground-model.json The compact softmax demo model and sample set used by the browser playground.
  8. digit-sample-grid.svg A small handwritten digit preview grid extracted from the training set.
  9. Handwritten digit project bundle Contains the source file, compressed datasets, submission files, browser model, and preview grid.
  10. cifar10_tiny_cnn.c source Single-file C tiny CNN with CIFAR-10 loading, convolution, pooling, softmax, and backpropagation.
  11. model_weights.bin sample weights Model weights generated by one local small-sample run.
  12. test_predictions.csv sample predictions Sample test prediction output from the CIFAR-10 tiny CNN.
  13. CNN project explanation PDF Companion explanation material for the CNN project.
  14. Virtual Mirror redacted code skeleton A redacted mld_chaffing_v2.py control-flow skeleton with secrets, node topology, and target lists removed.
  15. Virtual Mirror stress-test template A redacted CSV template for CPU, memory, peak threads, pulse rate, latency, and error measurements.
  16. Virtual Mirror classifier-evaluation template A CSV template for TP, FN, FP, TN, accuracy, precision, recall, F1, ROC-AUC, entropy, and JS divergence.
  17. Virtual Mirror resource notes Notes explaining why the public resources include only redacted code, test templates, and architecture context.
  18. AI Security Lab README Setup, safety boundaries, and quick-run commands for the AI Security series.
  19. AI Security Lab full bundle Includes safe toy scripts, result CSVs, risk register, attack-defense matrix, and architecture diagram.
  20. AI security risk register CSV risk register template for AI threat modeling and release review.
  21. AI attack-defense matrix Maps attack surface, toy demo, metric, and defensive control into one CSV table.
  22. AI Security Lab architecture diagram Shows threat modeling, robustness, data integrity, model privacy, and RAG guardrails.
  23. FGSM digits robustness script FGSM-style perturbation and accuracy-drop experiment for a local digits classifier.
  24. Data poisoning and backdoor toy script Demonstrates poison rate, trigger behavior, and attack success rate on digits.
  25. Model privacy and extraction toy script Outputs membership AUC, target accuracy, surrogate fidelity, and surrogate accuracy.
  26. RAG prompt injection guard toy script Uses a deterministic toy agent to demonstrate external-data demotion and tool-policy blocking.
  27. Deep Learning topic share card A 1200x630 SVG card for sharing the Deep Learning / CNN topic hub.
  28. Machine Learning From Scratch share card A 1200x630 SVG card for the K-means, Iris, and ML workflow topic hub.
  29. Student AI Projects share card A 1200x630 SVG card for handwritten digits, C classifiers, and browser demos.
  30. CNN convolution scan animation An 8-second Remotion animation showing how a 3x3 convolution kernel scans an input and builds a feature map.

Current route

  1. AI Basics Learning Roadmap Learning path step
  2. Machine Learning Workflow Learning path step
  3. Model Training and Evaluation Learning path step
  4. Neural Network Basics Learning path step
  5. Transformer Self-Attention Learning path step
  6. LLM Visualizer Learning path step
  7. Python AI Mini Practice Learning path step
  8. Handwritten Digit Dataset Basics Learning path step
  9. Handwritten Digit Softmax in C Learning path step
  10. Handwritten Digit Playground Notes Learning path step
  11. CIFAR-10 Tiny CNN Tutorial in C Learning path step
  12. High-Entropy Traffic Defense Notes Learning path step
  13. AI Security Threat Modeling Learning path step
  14. Adversarial Examples and Robust Evaluation Learning path step
  15. Data Poisoning and Backdoor Defense Learning path step
  16. Model Privacy and Extraction Defense Learning path step
  17. LLM, RAG, and Agent Security Learning path step

Next notes

  1. Add more image-classification and error-analysis cases
  2. Turn common metrics into a quick reference
  3. Add more AI security defense experiment notes