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.
Matching moments
19:14 MIN
Understanding the complexity of prompt injection attacks
Hacking AI - how attackers impose their will on AI
01:52 MIN
Understanding and mitigating prompt injection attacks
Prompt Injection, Poisoning & More: The Dark Side of LLMs
33:41 MIN
Manipulating AI with prompt injection and hidden commands
WeAreDevelopers LIVE - Is Software Ever Truly Accessible?
12:10 MIN
Understanding and defending against prompt injection attacks
Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails
13:31 MIN
Understanding and defending against prompt injection attacks
DevOps for AI: running LLMs in production with Kubernetes and KubeFlow
25:33 MIN
AI privacy concerns and prompt engineering
Coffee with Developers - Cassidy Williams -
14:26 MIN
Understanding the security risk of prompt injection
The shadows that follow the AI generative models
06:05 MIN
Understanding and demonstrating prompt injection attacks
The AI Security Survival Guide: Practical Advice for Stressed-Out Developers
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
25:17AI: Superhero or Supervillain? How and Why with Scott Hanselman
Scott Hanselman
31:12Using LLMs in your Product
Daniel Töws
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.
AI/ML Team Lead - Generative AI (LLMs, AWS)
Provectus
Remote
€96K
Senior
PyTorch
Tensorflow
Computer Vision
+2
Front End Engineering Manager ( Generative AI experience )
Accenture
GraphQL
React Native
Continuous Integration
{"@context":"https://schema.org/","@type":"JobPosting","title":"Software Engineer 2 - Full-Stack - Behavioral Security Products
Abnormal AI
Intermediate
Apache Kafka