WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2023 • Sep 27, 2023

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

Balázs Kiss

Are your machine learning models secretly harboring critical vulnerabilities? Discover how to defend your AI infrastructure against novel data poisoning attacks and traditional remote code execution exploits.

Pause
Mute Enter Fullscreen
#1 about 4 min

Understanding the landscape of AI capabilities and risks

How widespread AI adoption introduces new security challenges and failure modes.

#2 about 2 min

Addressing security flaws in AI-generated code

Why relying on AI for code generation can introduce outdated or flawed validation logic.

#3 about 2 min

Fundamental problems in machine learning model training

How overfitting, catastrophic forgetting, and bad input data compromise model reliability.

#4 about 2 min

Misusing AI for malware generation and physical evasion

How attackers leverage AI to automate exploitation, mutate malware, and bypass image recognition.

#5 about 2 min

Corrupting AI models and software supply chains

How malicious training data and compromised dependencies inject backdoors into AI applications.

#6 about 2 min

Utilizing industry threat models for AI security

Navigating frameworks from OWASP, NIST, and MITRE to understand and mitigate machine learning vulnerabilities.

#7 about 3 min

Categorizing threats across the machine learning lifecycle

Differentiating between novel machine learning threats and traditional software vulnerabilities affecting AI systems.

#8 about 1 min

Exploiting models through adversarial evasion samples

How imperceptible modifications to input data force machine learning models to make incorrect decisions.

#9 about 2 min

Poisoning data to manipulate model behavior

Injecting malicious data during training phases to alter decision boundaries and trigger targeted failures.

#10 about 2 min

Stealing confidential data through model extraction attacks

Using model inversion and excessive requests to extract sensitive training data or replicate proprietary models.

#11 about 3 min

Generating adversarial samples against digit recognition models

A live demonstration using the Adversarial Robustness Toolbox to trick an MNIST model into misreading financial digits.

#12 about 3 min

Preventing remote code execution in PyTorch models

Why loading unverified PyTorch models stored in the Pickle format exposes systems to arbitrary code execution.

#13 about 2 min

Securing developer wrapper code around machine learning models

Addressing traditional software bugs like exposed API keys and command injection in open-source AI wrappers.

#14 about 1 min

Replacing the Pickle format with secure serialization alternatives

Migrating to standard HDF5 or static serialization formats to prevent arbitrary code execution vulnerabilities.

Matching moments

3:00 min

Top security vulnerabilities for AI applications

Deepu Deepu · World Congress 2025

2:31 min

Emerging risks and attack vectors in AI systems

Matteo Meucci Matteo Meucci · Europe 2026 Virtual

3:18 min

Core AI security risks and data poisoning

Liran Tal Liran Tal · LIVE

4:55 min

Core principles of manipulating artificial intelligence models

Mirko Ross · World Congress 2023

1:46 min

Introduction to machine learning security and robustness

Nura Kawa · World Congress 2023

2:31 min

Understanding data poisoning and model bias risks

Keno Dreßel Keno Dreßel · World Congress 2025

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
almost 3 years ago

Demografie nutzen um jedem Bewerber das passende Angebot zu machen!

Nathalie Gierth

Guided Memory Management: Rust's Ownership Model thumbnail
0:18
almost 3 years ago

Guided Memory Management: Rust's Ownership Model

Stefan Baumgartner

Passwordless future: WebAuthn and Passkeys in practice thumbnail
32:32
almost 3 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
almost 3 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
almost 3 years ago

Building Reliable Serverless Applications with AWS CDK and Testing

Raphael Manke

Related videos

Hacking AI - how attackers impose their will on AI thumbnail
27:02
World Congress 2023 • almost 3 years ago

Hacking AI - how attackers impose their will on AI

Mirko Ross

Machine Learning: Promising, but Perilous thumbnail
27:19
World Congress 2023 • about 3 years ago

Machine Learning: Promising, but Perilous

Nura Kawa

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

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

Mackenzie

Prompt Injection, Poisoning & More: The Dark Side of LLMs thumbnail
23:24
World Congress 2025 • about 1 year ago

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

Keno Dreßel

Confuse, Obfuscate, Disrupt: Using Adversarial Techniques for Better AI and True Anonymity thumbnail
27:34
World Congress 2025 • about 1 year ago

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

David vonThenen

Can Machines Dream of Secure Code? Emerging AI Security Risks in LLM-driven Developer Tools thumbnail
35:37
LIVE • about 2 years ago

Can Machines Dream of Secure Code? Emerging AI Security Risks in LLM-driven Developer Tools

Liran Tal

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.