liveBook · Manning

Adversarial input

Also called adversarial example

An input crafted, selected, or modified to exploit a system’s weaknesses or induce incorrect, unsafe, or otherwise unintended behavior.

How 5 Manning books explain it

LLMs in Production

The study and use of inputs or models designed to manipulate, evade, or expose weaknesses in machine-learning systems.

How it is used
Frames adversarial inputs as security risks for deployed language-model services.
How deep it goes
Explains attack mechanisms and safeguard trade-offs qualitatively, without an implementation walkthrough.
Examples
Uses a misclassified frog image, a fabricated cola recipe, and generated-text detection to illustrate adversarial behavior.
What you can do after
Evaluate and understand attack risks, suspicious outputs, and language-filtering trade-offs.

Read how LLMs in Production explains adversarial input →

Sutskever's List

An 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.

How it is used
Uses adversarial examples to challenge claims that benchmark success reflects human-like understanding or general robustness.
How deep it goes
Defines the failure and its significance, but does not explain how perturbations are constructed.
Examples
Uses imperceptible input perturbations and a separate Google Photos mislabeling incident to illustrate brittleness.
What you can do after
Evaluate why benchmark performance alone does not establish robust visual understanding.

Read how Sutskever's List explains adversarial input →

Generative AI in Action

An adversarial example is an input modified or crafted to cause a machine-learning model to produce an incorrect or undesirable output.

How it is used
Tests LLM resilience against harmful, bad, and edge-case inputs during enterprise red-teaming.
How deep it goes
Defines adversarial attacks and names generation tools, but does not explain attack algorithms or mathematical internals.
Examples
Uses TextAttack and a SLURM pipeline to run attacks and evaluate completions across Llama 2, Baichuan2, Mistral, and other models.
What you can do after
Apply it via TextAttack and attack pipelines to evaluate model resilience against problematic inputs.

Read how Generative AI in Action explains adversarial input →

Deep Learning with R, Third Edition

An adversarial example is an input deliberately or naturally modified in a small way that causes a machine-learning model to produce an incorrect output.

How it is used
Diagnoses brittleness in image models and language models by showing how minor input changes can cause major errors.
How deep it goes
Explains the idea through gradient ascent and examples, but does not develop attack algorithms or defenses.
Examples
Uses a panda-to-gibbon image change and an Alice in Wonderland riddle with altered numerical values.
What you can do after
Evaluate how apparently harmless input changes can expose mismatches between model predictions and human judgment.

Read how Deep Learning with R, Third Edition explains adversarial input →

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.

How it is used
Exposes the brittleness of deep learning models and the mismatch between their input-output mappings and human perception.
How deep it goes
Explains the gradient-ascent mechanism and a panda-to-gibbon example, without detailing attack algorithms or defenses.
Examples
Uses a panda image modified toward the gibbon class and a figure illustrating imperceptible classification-changing perturbations.
What you can do after
Evaluate/understand how small input perturbations can cause confident model misclassification.

Read how Deep Learning with Python, Third Edition explains adversarial input →

Also covered in

What to know first

Related concepts

Questions about adversarial input

What is adversarial input?

An input crafted, selected, or modified to exploit a system’s weaknesses or induce incorrect, unsafe, or otherwise unintended behavior.

Which Manning books explain adversarial input?

LLMs in Production, Sutskever's List, Generative AI in Action, Deep Learning with R, Third Edition and Deep Learning with Python, Third Edition.

What should I know before learning adversarial input?

Manning books that teach adversarial input usually introduce language model, accuracy, convolutional neural network and fine-tuning first.

What kinds of adversarial input are there?

Kinds of adversarial input include prompt injection.

What is adversarial input a kind of?

Adversarial input is a kind of input. An input is information, a value, or an action supplied to a system, program, or computation for processing or to influence its behavior.

What is adversarial input also called?

Adversarial input is also called adversarial example.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.