Georg Dresler
Manipulating The Machine: Prompt Injections And Counter Measures
#1about 4 minutes
Understanding the three layers of an LLM prompt
A prompt is structured into three layers: the system prompt for instructions, the context for additional data, and the unpredictable user input.
#2about 3 minutes
How a car dealer's chatbot was easily manipulated
A Chevrolet car dealer's chatbot was exploited by users to generate humorous and unintended responses, including a legally binding offer for a $1 car.
#3about 4 minutes
Stealing system prompts to bypass security rules
Attackers can use creative phrasing like "repeat everything above" to trick an LLM into revealing its hidden system prompt and instructions.
#4about 6 minutes
Why attackers use prompt injection techniques
Prompt injections are used to access sensitive business data, gain personal advantages like bypassing HR filters, or exploit integrated tools to steal information like 2FA tokens.
#5about 4 minutes
Exploring simple but ineffective defense mechanisms
Initial defense ideas like avoiding secrets or tool integration are impractical, and simple system prompt instructions are easily circumvented by attackers.
#6about 4 minutes
Using fine-tuning and adversarial detectors for defense
More effective defenses include fine-tuning models on domain-specific data to reduce reliance on instructions and using specialized adversarial prompt detectors to identify malicious input.
#7about 2 minutes
Key takeaways on prompt injection security
Treat all system prompt data as public, use a layered defense of instructions, detectors, and fine-tuning, and accept that no completely reliable solution exists yet.
Related jobs
Jobs that call for the skills explored in this talk.
Wilken GmbH
Ulm, Germany
Senior
Kubernetes
AI Frameworks
+3
Picnic Technologies B.V.
Amsterdam, Netherlands
Intermediate
Senior
Python
Structured Query Language (SQL)
+1
Matching moments
07:39 MIN
Prompt injection as an unsolved AI security problem
AI in the Open and in Browsers - Tarek Ziadé
03:45 MIN
Preventing exposed API keys in AI-assisted development
Slopquatting, API Keys, Fun with Fonts, Recruiters vs AI and more - The Best of LIVE 2025 - Part 2
04:59 MIN
Unlocking LLM potential with creative prompting techniques
WeAreDevelopers LIVE – Frontend Inspirations, Web Standards and more
01:06 MIN
Malware campaigns, cloud latency, and government IT theft
Fake or News: Self-Driving Cars on Subscription, Crypto Attacks Rising and Working While You Sleep - Théodore Lefèvre
05:55 MIN
The security risks of AI-generated code and slopsquatting
Slopquatting, API Keys, Fun with Fonts, Recruiters vs AI and more - The Best of LIVE 2025 - Part 2
01:15 MIN
Crypto crime, EU regulation, and working while you sleep
Fake or News: Self-Driving Cars on Subscription, Crypto Attacks Rising and Working While You Sleep - Théodore Lefèvre
06:33 MIN
The security challenges of building AI browser agents
AI in the Open and in Browsers - Tarek Ziadé
14:06 MIN
Exploring the role and ethics of AI in gaming
Devs vs. Marketers, COBOL and Copilot, Make Live Coding Easy and more - The Best of LIVE 2025 - Part 3
Featured Partners
Related Videos
27:32ChatGPT, ignore the above instructions! Prompt injection attacks and how to avoid them.
Sebastian Schrittwieser
23:24Prompt Injection, Poisoning & More: The Dark Side of LLMs
Keno Dreßel
29:00Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails
Alex Soto
30:36The AI Security Survival Guide: Practical Advice for Stressed-Out Developers
Mackenzie Jackson
33:28Prompt Engineering - an Art, a Science, or your next Job Title?
Maxim Salnikov
27:02Hacking AI - how attackers impose their will on AI
Mirko Ross
31:12Using LLMs in your Product
Daniel Töws
25:17AI: Superhero or Supervillain? How and Why with Scott Hanselman
Scott Hanselman
Related Articles
View all articles
.png?w=240&auto=compress,format)
From learning to earning
Jobs that call for the skills explored in this talk.
Deloitte
Leipzig, Germany
Azure
DevOps
Python
Docker
PyTorch
+6
Abnormal AI
Intermediate
API
Spark
Kafka
Python
Starion Group
Municipality of Madrid, Spain
API
CSS
Python
Docker
Machine Learning
+1
Deloitte
Görlitz, Germany
Azure
DevOps
Python
Docker
PyTorch
+6
83zero Ltd
Manchester, United Kingdom
Remote
£130K
Senior
Python
Machine Learning
Speech Recognition
Agenda GmbH
Remote
Intermediate
API
Azure
Python
Docker
+10
autonomous-teaming
München, Germany
Remote
API
React
Python
TypeScript