Balázs Kiss
A hundred ways to wreck your AI - the (in)security of machine learning systems
#1about 4 minutes
The security risks of AI-generated code
AI systems can generate code quickly but may introduce vulnerabilities or rely on outdated practices, highlighting that all AI systems are fundamentally code and can be exploited.
#2about 5 minutes
Fundamental AI vulnerabilities and malicious misuse
AI systems are prone to classic failures like overfitting and can be maliciously manipulated through deepfakes, chatbot poisoning, and adversarial patterns.
#3about 1 minute
Exploring threat modeling frameworks for AI security
Several organizations like OWASP, NIST, and MITRE provide threat models and standards to help developers understand and mitigate AI security risks.
#4about 6 minutes
Deconstructing AI attacks from evasion to model stealing
Attack trees categorize novel threats like evasion with adversarial samples, data poisoning to create backdoors, and model stealing to replicate proprietary systems.
#5about 2 minutes
Demonstrating an adversarial attack on digit recognition
A live demonstration shows how pre-generated adversarial samples can trick a digit recognition model into misclassifying numbers as zero.
#6about 5 minutes
Analyzing supply chain and framework security risks
Security risks extend beyond the model to the supply chain, including backdoors in pre-trained models, insecure serialization formats like Pickle, and vulnerabilities in ML frameworks.
#7about 1 minute
Choosing secure alternatives to the Pickle model format
The HDF5 format is recommended as a safer, industry-standard alternative to Python's insecure Pickle format for serializing machine learning models.
Related jobs
Jobs that call for the skills explored in this talk.
Machine Learning Engineer
Picnic Technologies B.V.
Amsterdam, Netherlands
Intermediate
Senior
Python
Structured Query Language (SQL)
+1
SENIOR AI SOLUTIONS ENGINEER (M/W/D) Based in Germany
Wilken GmbH
Ulm, Germany
Senior
Kubernetes
AI Frameworks
+3
Matching moments
20:06 MIN
New security vulnerabilities and monitoring for AI systems
The State of GenAI & Machine Learning in 2025
10:01 MIN
Navigating the new landscape of AI and cybersecurity
From Monolith Tinkering to Modern Software Development
10:01 MIN
The complex relationship between AI and cybersecurity
Panel: How AI is changing the world of work
09:22 MIN
Understanding the fundamental security risks in AI models
Can Machines Dream of Secure Code? Emerging AI Security Risks in LLM-driven Developer Tools
03:07 MIN
The dual nature of machine learning's power
Machine Learning: Promising, but Perilous
00:20 MIN
Understanding AI security risks for developers
The AI Security Survival Guide: Practical Advice for Stressed-Out Developers
00:04 MIN
Understanding the current state of AI security challenges
Delay the AI Overlords: How OAuth and OpenFGA Can Keep Your AI Agents from Going Rogue
09:01 MIN
The security risks of AI agents and generated code
Five things in tech that matter and we have to make work
Featured Partners
Related Videos
27:02Hacking AI - how attackers impose their will on AI
Mirko Ross
27:19Machine Learning: Promising, but Perilous
Nura Kawa
30:36The AI Security Survival Guide: Practical Advice for Stressed-Out Developers
Mackenzie Jackson
31:19Skynet wants your Passwords! The Role of AI in Automating Social Engineering
Wolfgang Ettlinger & Alexander Hurbean
29:00Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails
Alex Soto
24:33GenAI Security: Navigating the Unseen Iceberg
Maish Saidel-Keesing
27:26Staying Safe in the AI Future
Cassie Kozyrkov
23:24Prompt Injection, Poisoning & More: The Dark Side of LLMs
Keno Dreßel
Related Articles
View all articles
From learning to earning
Jobs that call for the skills explored in this talk.
AI Systems and MLOps Engineer for Earth Observation
Forschungszentrum Jülich GmbH
Jülich, Germany
Intermediate
Senior
Linux
Docker
AI Frameworks
Machine Learning
AI Engineer / Machine Learning Engineer / KI-Entwickler - Schwerpunkt Cloud & MLOps
Agenda GmbH
Rosenheim, Germany
Intermediate
API
Azure
Python
Docker
PyTorch
+9
Student project: Optimizing Open-set Recognition Methods for Reliable Real-world AI Systems
Imec
Azure
Python
PyTorch
TensorFlow
Computer Vision
+1
Machine Learning Engineer (AI Core Team)
Manychat
Barcelona, Spain
Intermediate
Python
Docker
PyTorch
FastAPI
PostgreSQL
+3
Remote ML Researcher - Benchmarking & Real-World AI
Taskify AI
Municipality of Madrid, Spain
Remote
Machine Learning
Junior ML Engineer - AI Systems & Frameworks (Barcelona)
10xengineers
Barcelona, Spain
Junior
API
C++
Python
Machine Learning
AI Engineer / Machine Learning Engineer / KI-Entwickler
Agenda GmbH
Raubling, Germany
Remote
Intermediate
API
Azure
Python
Docker
+10
ML Security Tools & Threat Modeling Engineer
NXP Semiconductors
Gratkorn, Austria
API
Python
Machine Learning