Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

Defending Against Generative AI-Based Fraud

Name: Defending Against Generative AI-Based Fraud
Rating: 4.4 (134 reviews)

How to defend against fraudulent emails, deepfakes, and many other types of fraud attempts done with generative AI.

Role Play

Created byVasco Patrício

Last updated 3/2026

English

What you'll learn

How to prevent fraud attempts performed with generative AI
How to identify generative/false/synthetic content
How to develop new defense mechanisms against these new generative threats
How to integrate new defense mechanisms into your current organization

Course content

11 sections • 75 lectures • 12h 44m total length

Course Intro3:16
Explore how fraud leverages generative AI across text, image, audio, and video; learn defenses, validation, authentication, and organizational workflows to implement protection.
Useful Information2:09

Module Intro2:15
Explore the fundamentals of generative AI and fraud, review model types such as GANs, LLMs, and VAEs, and learn how gen AI accelerates fraud while outlining defenses.
Fundamentals of Generative AI14:46
Understand how generative AI creates new content, which models power it, and which systemic risks it introduces.
Fundamentals of Fraud14:05
Explain how fraudsters misrepresent identities, manipulate systems, and exploit human and process weaknesses for financial gain.
Fraud with Generative AI17:45
Analyze how generative AI enables scalable, realistic, and evasive fraud—and how organizations adapt their defenses.
Module Outro2:03
Explore the fundamentals of generative AI, its models, biases, and how it intersects with fraud, including automation, scaling, and evolving defenses.
Role Play Interview: Fundamentals
Intro to Udemy Labs3:00
Lab: AI-Enhanced Fraud Risk Simulator1:24

Module Intro2:22
Explore how fraudsters deploy generative content across text, image, audio, and video, detailing models, deployment channels, data needs, and detection methods.
Overview14:48
Map the main generative media types used in social engineering and understand their creation and detection characteristics.
Text11:34
Recognize how AI-generated text enables scalable, context-aware fraud and how it is distributed and detected.
Image16:21
Understand how generative images support document forgery and synthetic identities, and how visual fraud is mitigated.
Audio16:41
Analyze how AI-generated audio enables voice impersonation and vishing, and how organizations defend against it.
Video18:10
Explain how generative video supports high-impact impersonation and deepfake scams, and how these attacks are countered.
Module Outro2:03
Explore how generative ai fuels fraud across text, image, audio, and video, detailing models, data needs, deployment, detection, and mitigation strategies such as mfa.
Role Play Interview: Mediums and Channels
Lab: Channel Exploitation Simulator1:44

Module Intro3:08
Explore how fraudsters use generative AI to create false documents, manipulate payments, abuse claims, and access data at scale, with four focused attack lessons.
False Documents/Accounts13:51
Understand how generative AI enables the creation of synthetic documents and identities, and how organizations detect and mitigate them.
Payment Process Abuse16:27
Explain how generative AI is used to exploit payment workflows and how controls limit unauthorized transfers.
Claims Process Abuse14:30
Identify how generative AI amplifies insurance and reimbursement fraud and how large-scale claim abuse is detected.
Data/Account Exploitation13:41
Recognize how generative AI enables large-scale account compromise and how continuous verification reduces impact.
Module Outro2:15
Explore how fraudsters leverage generative AI to attack four areas—false documents and accounts, payment process abuse, claims process abuse, and data or account exploitation.
Role Play Interview: Attack Approaches
Lab: Fraud Method Builder1:48

Module Intro2:42
Explore defenses against fraud driven by generative ai, focusing on document verification, behavioral analysis, multifactor authentication, adaptive authentication, and multichannel identity verification.
Document Verification15:08
Evaluate documents using layered forensic, consistency, and AI-based checks to detect generative forgeries.
Behavioral Analysis15:17
Detect fraud by identifying deviations from established user behavior across transactions, devices, and interactions.
Additional Authentication14:18
Strengthen fraud defenses by dynamically escalating authentication requirements based on assessed risk.
Multichannel ID Verification10:05
Validate identities by combining multiple verification channels to reduce reliance on any single, forgeable signal.
Module Outro2:36
defend against fraud that uses generative ai by applying document verification, behavioral analysis, adaptive and multifactor authentication, and multichannel identity verification to assess risk and anomalies.
Role Play Interview: Defense Techniques
Lab: Fraud Defense Stack Simulator1:54

Module Intro3:04
Defending against generative AI-based fraud, this module outlines protection strategies and shows how to integrate LLMs with existing models for parallel analysis, enriched outputs, and incident response.
Changes Due to Generative AI13:30
Adapt existing fraud defenses to counter the scale, realism, and speed introduced by generative AI attacks.
Parallel Anomaly Analysis11:35
Use large language models in parallel with traditional detection systems to identify complementary fraud signals and blind spots.
Enriching Model Outputs15:40
Enhance fraud model outputs with contextual validation, explanation, and prioritization using LLMs.
Detecting and Triaging Attacks16:25
Prioritize and route generative-AI-enabled threats by risk, impact, and novelty across detection pipelines.
Responding and Recovering17:45
Contain generative-AI-driven attacks, investigate root causes, and reinforce systems to improve future resilience.
Module Outro2:20
Outlining practical protections against generative AI-driven fraud and social engineering, this module covers workflows, tools, defenses, parallel analysis with LLMs, enriching outputs, and effective detection, triage, and response.
Role Play Interview: Implementing Protection
Lab: Enterprise Gen AI Fraud Response Simulator1:53

Module Intro3:16
Learn practical validation techniques for evaluating AI-generated outputs, including six sweeps: overview, assumption, grounding, consistency, specificity and capability, and negative evidence.
Validation Overview & Process12:27
Adopt a structured validation discipline that separates plausibility from truth and enforces judgment before trust.
Assumption Sweep7:23
Expose hidden assumptions, incentives, and directional framing that subtly push conclusions or actions.
Grounding Sweep9:44
Separate fluent narrative from verifiable evidence by demanding traceable sources and factual support.
Consistency Sweep12:17
Test whether the parts of an output align logically, structurally, and contextually across sections and iterations.
Specificity and Capability Sweep12:31
Challenge confident detail by asking whether the model realistically had the knowledge or authority to make such claims.
Negative Evidence Sweep9:39
Identify what is missing (constraints, trade-offs, risks, or verification paths), that should naturally be present in a complete answer.
Module Outro2:57
Explore six sweeps—validation, assumption, grounding, consistency, specificity and capability, and negative evidence—to judge Gen AI outputs, identify errors, hidden assumptions, and missing evidence.

Module Intro3:38
Learn what AI is and how it works, explore foundation models and AI adoption across industries, and examine the three tiers of usefulness and work modes for effective collaboration.
Where We Are16:50
Contextualize the current state of GenAI by understanding foundation models, their uneven impact on work, and the cognitive, emotional, and organizational shifts they introduce.
What Gen AI Can Actually Do17:26
Classify GenAI use cases by usefulness and risk, distinguishing tasks where it reliably augments work from those where it produces shallow reasoning, instability, or dangerous errors.
How Gen AI Changes Work16:58
Evaluate how GenAI changes professional work by shifting effort from execution to automation, requiring structured reasoning, orchestration, and new validation responsibilities.
Technical Aspects of Gen AI30:02
Understand the technical foundations of GenAI systems—including models, context, embeddings, and hallucinations—to better interpret outputs, limitations, and failure modes.
Common Pain Points23:00
Identify common organizational and human pain points in GenAI adoption, including unrealistic expectations, workflow misalignment, trust erosion, and cognitive degradation.
Module Outro2:14
Explore this module outro, summarizing AI essentials—what AI is and isn’t, what it can and can’t do, seven pain points, the three tiers of tasks, and Genai basics like tokens.
Role Play: Teaching Gen AI Literacy

Module Intro3:57
Explore how AI models prevent fraud in banking and how JNI augments these models, covering rules based systems, anomaly detectors, and network graphs with transaction, user, payment, merchant data Genai.
Process, Models, Expertise10:47
Explore rules-based, anomaly detection, and network analysis models for fraud prevention, and learn a four-step process: data gathering, assumptions, model building, validation, and deployment with essential expertise.
Data and Features12:01
Identify data sources for fraud modeling—transaction and authorization data, account history, historical fraud data, and behavioral signals—and apply rule-based, anomaly, and network models to detect fraud from these features.
Rules-Based Systems: Usual Approach19:03
Explore rules-based fraud detection using if-then blocks, boolean logic, and thresholds to flag transactions, prioritize actions, and analyze coverage, bypass analysis, and maintenance challenges.
Rules-Based Systems:: With Gen AI10:29
Explore rules-based fraud detection enhanced by JNI, creating and refining intelligent rules, dynamically calibrating thresholds, and translating between human language and rules for faster, targeted detection.
Anomaly Detectors: Usual Approach15:08
Learn how anomaly detectors build behavioral baselines across multiple dimensions to detect deviations in fraud prevention, addressing cold start and explainability while evaluating precision, recall, F1, and ROC AUC.
Anomaly Detectors: With Gen AI12:56
Enhance anomaly detectors for fraud with GenAI, creating multi-modal behavioral baselines, adding context, and generating human-readable justifications to reduce false positives and detect more subtle fraud.
Network Models: Usual Approach17:30
Map entities as nodes and relationships as edges for coordinated fraud detection with network models. Analyze network structure to reveal fraud rings while noting data structuring needs and scalability.
Network Models: With Gen AI10:27
Explore how network models detect fraud and how generative ai enhances entity resolution. Learn to explain complex outputs in human language and analyze network evolution over time.
Module Outro1:58
Learn how ai models, rules-based systems, anomaly detectors, and network models detect and prevent fraud in banking, enhanced by Genai insights.

Requirements

A basic knowledge of fraud and defenses against it is advised (e.g. what is payment fraud and how to prevent it) is recommended, but not necessary
A basic knowledge of what generative AI is, and the content it can create is recommended, but not necessary

Description

BEATING FRAUD

Fraud, including payment fraud and insurance fraud, is one of the biggest problems for organizations.

And new advances in terms of generative AI have only made this worse.

In the world of today, organizations and individuals must be able to not only resist fraud attempts, but resist when they leverage generative AI - which, in many cases, means faster, larger-scale and more sophisticated attacks.

This course will teach you how to protect against fraud that leverages generative AI.

LET ME TELL YOU... EVERYTHING.

Some people - including me - love to know what they're getting in a package.

And by this, I mean, EVERYTHING that is in the package.

So, here is a list of everything that this course covers:

You'll learn the basics of generative AI and what it can do, including common models and families of models, the characteristics of generative content, and how it can be misused due to negligence or active malevolence (including biases, misinformation, impersonation and more);
You'll learn the basics of fraud and its main types (identity theft, payment fraud, investment fraud, insurance fraud, account takeover), and the main factors enabling it (technological gaps, human error, process weaknesses, data breaches);
You'll learn how fraud is accelerated by generative AI (mass automation, increased authenticity, pattern evasion, synthetic identity creation, etc) and its effect on the major approaches (document forgery, transaction manipulation, synthetic identity fraud, claims fraud, etc);
You'll learn about an overview of the major generative content types used in fraud attacks (text, image, audio and video), including the specific approaches that each leverage, the model training requirements and data required for attackers to train such models, and how each type can be detected;
You'll learn about generative text in fraud, including the models that allow it such as LLMs, the distribution channels such as email, SMS, chats, the data required to train such models, and detection mechanisms such as behavioral analysis, authentication and text validations;
You'll learn about generative image in fraud, including the models that allow it such as GANs or diffusion models, the distribution channels such as deceptive documents and images in email attachments or submission portals, the data required to train such models, and detection mechanisms such as watermarks, behavioral detection or MFA;
You'll learn about generative audio in fraud, including the models that allow it such as GANs or TTS, the distribution channels such as voice messaging software or for calls, the data required to train such models, and detection mechanisms such as MFA factors, callbacks, or training employees;
You'll learn about generative video in fraud, including the models that allow it such as GANs for video or deep learning models, the distribution channels such as communication tools or submission portals, the data required to train such models, and detection mechanisms such as verifying communications, anti-deepfake software, MFA;

MY INVITATION TO YOU

Remember that you always have a 30-day money-back guarantee, so there is no risk for you.

Also, I suggest you make use of the free preview videos to make sure the course really is a fit. I don't want you to waste your money.

If you think this course is a fit, and can take your knowledge of dealing with change to the next level... it would be a pleasure to have you as a student.

See on the other side!

Who this course is for:

Fraud prevention/cybersecurity engineers focusing on preventing fraud
Data privacy and security professionals that want to better protect their organization's data
Employees of any organization that want to be better protected against fraud

Defending Against Generative AI-Based Fraud

What you'll learn

Explore related topics

Course content

Course Intro2 lectures • 5min

Fundamentals8 lectures • 55min

Attack Mediums/Channels9 lectures • 1hr 24min

Gen AI Attack Approaches8 lectures • 1hr 6min

Defense Techniques8 lectures • 1hr 2min

Implementing Protection9 lectures • 1hr 22min

Course Outro1 lecture • 3min

Specialized Module: Judging Gen AI Outputs8 lectures • 1hr 10min

Specialized Module: Gen AI Literacy8 lectures • 1hr 50min

Specialized Module: Financial Modeling with Gen AI for Fraud Prevention10 lectures • 1hr 54min

Requirements

Description

Who this course is for: