WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2023 • Nov 10, 2023

Hacking AI - how attackers impose their will on AI

Mirko Ross

A simple printed sticker can trick an autonomous vehicle into dangerous misclassifications. Discover how attackers manipulate AI with mathematical noise, and learn to secure your machine learning pipelines.

Pause
Mute Enter Fullscreen
#1 about 5 min

Core principles of manipulating artificial intelligence models

How the statistical nature of AI systems leaves them susceptible to data poisoning and unexpected outputs.

#2 about 4 min

Missing input validation practices in the artificial intelligence industry

Why failing to sanitize training data creates security vulnerabilities similar to legacy web application flaws.

#3 about 8 min

Exploiting image recognition systems with physical adversarial attacks

How adding calculated mathematical disturbance to two dimensional objects forces neural networks into dangerous misclassifications.

#4 about 2 min

Executing adversarial attacks on three dimensional physical objects

How embedding disturbance patterns into physical models guarantees misclassification across different camera angles.

#5 about 3 min

Defending visual artificial intelligence models against data poisoning

How reducing image bit depth effectively strips malicious mathematical noise from visual inputs.

#6 about 6 min

Prompt injection vulnerabilities and contextual mitigation testing challenges

Why complex contextual prompts easily circumvent manual ethical constraints and scale poorly for foundational models.

#7 about 3 min

Generating adversarial patterns and defending consumer machine learning models

How automated systems generate disturbance patterns and why utilizing third-party models remains inherently risky.

Matching moments

1:44 min

Corrupting AI models and software supply chains

Balázs Kiss · WWC 2023

2:31 min

Emerging risks and attack vectors in AI systems

Matteo Meucci Matteo Meucci · Europe 2026 Virtual

1:36 min

Misusing AI for malware generation and physical evasion

Balázs Kiss · WWC 2023

8:04 min

Understanding AI chatbot vulnerabilities and stateful attacks

Sebastian Messingfeld Sebastian Messingfeld · WWC Europe 2026

3:00 min

Top security vulnerabilities for AI applications

Deepu Deepu · WWC 2025

3:18 min

Core AI security risks and data poisoning

Liran Tal Liran Tal · LIVE

More from World Congress 2023

The year 3000, a brief history of Web Development thumbnail
25:30
over 2 years ago

The year 3000, a brief history of Web Development

Lorenzo Pieri

Demografie nutzen um jedem Bewerber das passende Angebot zu machen! thumbnail
8:52
over 2 years ago

Demografie nutzen um jedem Bewerber das passende Angebot zu machen!

Nathalie Gierth

Guided Memory Management: Rust's Ownership Model thumbnail
0:18
over 2 years ago

Guided Memory Management: Rust's Ownership Model

Stefan Baumgartner

Passwordless future: WebAuthn and Passkeys in practice thumbnail
32:32
over 2 years ago

Passwordless future: WebAuthn and Passkeys in practice

Clemens Hübner

External Secrets Operator: the secrets management toolbox for self-sufficient teams thumbnail
30:07
over 2 years ago

External Secrets Operator: the secrets management toolbox for self-sufficient teams

Moritz Johner

Building Reliable Serverless Applications with AWS CDK and Testing thumbnail
25:18
over 2 years ago

Building Reliable Serverless Applications with AWS CDK and Testing

Raphael Manke

Upcoming sessions on this topic

Open session

World Congress 2026 North America

The Things Your AI Isn't Telling You

Desmond Lamptey

Lead Software Engineer @ Capital One

Desmond Lamptey
Open session

World Congress 2026 North America

SecurePrompt: Building a Pre-Flight Security Layer for Agentic AI

Ravi Sastry Kadali

AI/ML Engineer at General Motors

Ravi Sastry Kadali
Open session

World Congress 2026 North America

Securing AI Agent Infrastructure: Identity, Attestation, and Trust at Scale

Abdel Fane

Founder of OpenA2A

Abdel Fane
Open session

World Congress 2026 North America

AI That Argues With Itself: Building Self-Debating Systems That Catch Their Own Bugs

Shreya Singhal

AI Applied Scientist at Claritev

Shreya Singhal
Open session

World Congress 2026 North America

Responsible AI Architecture with Zero Trust Agents

Ashok Prakash

Staff ML Engineer at Apple

Ashok Prakash
Open session

World Congress 2026 North America

You Can’t Re-Run Sunlight: Designing ML Data Architectures for Physical AI

An Phan

Senior Data Infrastructure Engineer @ Hippo Harvest

An Phan

Related videos

A hundred ways to wreck your AI - the (in)security of machine learning systems thumbnail
24:23
WWC 2023 • almost 3 years ago

A hundred ways to wreck your AI - the (in)security of machine learning systems

Balázs Kiss

The AI Security Survival Guide: Practical Advice for Stressed-Out Developers thumbnail
30:36
WWC 2024 • almost 2 years ago

The AI Security Survival Guide: Practical Advice for Stressed-Out Developers

Mackenzie

Confuse, Obfuscate, Disrupt: Using Adversarial Techniques for Better AI and True Anonymity thumbnail
27:34
WWC 2025 • 12 months ago

Confuse, Obfuscate, Disrupt: Using Adversarial Techniques for Better AI and True Anonymity

David vonThenen

Prompt Injection, Poisoning & More: The Dark Side of LLMs thumbnail
23:24
WWC 2025 • 12 months ago

Prompt Injection, Poisoning & More: The Dark Side of LLMs

Keno Dreßel

Manipulating The Machine: Prompt Injections And Counter Measures thumbnail
27:10
WWC 2024 • almost 2 years ago

Manipulating The Machine: Prompt Injections And Counter Measures

Georg

Machine Learning: Promising, but Perilous thumbnail
27:19
WWC 2023 • almost 3 years ago

Machine Learning: Promising, but Perilous

Nura Kawa

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.