How deeply does Deep Learning with Python, Third Edition cover adversarial input?

Explains the gradient-ascent mechanism and a panda-to-gibbon example, without detailing attack algorithms or defenses.

Adversarial input

As explained in Deep Learning with Python, Third Edition

Inputs intentionally or effectively perturbed to cause a model to make a wrong prediction despite minimal change to the original example.

An adversarial example is an input changed just enough to make a deep learning model misclassify it. The change may be nearly invisible to people while radically altering the model’s prediction, exposing a gap between machine and human perception. section 19.1.2

Turning a panda into a gibbon

Starting with a panda photograph, apply gradient ascent in input space to increase the network’s prediction for the gibbon class. The resulting image still looks like a panda to people, but the network classifies it as a gibbon. section 19.1.2

Practical takeaways:

Treat high confidence as potentially brittle: small input changes can produce a different prediction. section 19.1.2
Do not confuse humanly minor changes with modelically minor changes; the two systems may respond very differently to the same image. section 19.1.2

How Deep Learning with Python, Third Edition covers it

Cover of Deep Learning with Python, Third Edition

liveBook manning.com

Read Deep Learning with Python, Third Edition on liveBook Get the book at manning.com

Also explained in

liveBook manning.com

LLMs in ProductionThe study and use of inputs or models designed to manipulate, evade, or expose weaknesses in machine-learning systems.
liveBook manning.com

Sutskever's ListAn adversarial example is an input deliberately perturbed in a way that is often imperceptible to humans but causes a model to make an incorrect prediction.
liveBook manning.com

Generative AI in ActionAn adversarial example is an input modified or crafted to cause a machine-learning model to produce an incorrect or undesirable output.
liveBook manning.com

Deep Learning with R, Third EditionAn adversarial example is an input deliberately or naturally modified in a small way that causes a machine-learning model to produce an incorrect output.

Compare how 5 books explain adversarial input →

Related concepts

red-teamingused by · Red-teaming is an adversarial assessment practice that deliberately simulates attacks or uses challenging inputs to identify a system’s vulnerabilities, failures, or unsafe behavior.
TextAttackused by · TextAttack is an open-source Python framework for generating adversarial examples, augmenting data, training NLP models, and evaluating their robustness.
poisoning attackimplemented by · A poisoning attack deliberately corrupts data, a learning process, or model artifacts to compromise a machine-learning system’s behavior or outputs.
robustnessmeasures · Robustness is the ability of a system or model to maintain acceptable behavior or performance despite variations, disturbances, faults, or challenging conditions.
prompt injectionincludes · Prompt injection is an attack that introduces instructions through input or context to manipulate an AI system’s behavior or override its intended instructions.
predicted valueproduces · A predicted value is an estimated outcome or output that a model produces for given input values.

This explainer was generated by Manning's knowledge graph from the text of Deep Learning with Python, Third Edition. The section links point to the parts of the book it draws on.