Sebastian Schrittwieser
ChatGPT, ignore the above instructions! Prompt injection attacks and how to avoid them.
#1about 2 minutes
The rapid adoption of LLMs outpaces security practices
New technologies like large language models are often adopted quickly without established security best practices, creating new vulnerabilities.
#2about 4 minutes
How user input can override developer instructions
A prompt injection occurs when untrusted user input contains instructions that hijack the LLM's behavior, overriding the developer's original intent defined in the context.
#3about 4 minutes
Using prompt injection to steal confidential context data
Attackers can use prompt injection to trick an LLM into revealing its confidential context or system prompt, exposing proprietary logic or sensitive information.
#4about 4 minutes
Expanding the attack surface with plugins and web data
LLM plugins that access external data like emails or websites create an indirect attack vector where malicious prompts can be hidden in that external content.
#5about 2 minutes
Prompt injection as the new SQL injection for LLMs
Prompt injection mirrors traditional SQL injection by mixing untrusted data with developer instructions, but lacks a clear mitigation like prepared statements.
#6about 3 minutes
Why simple filtering and encoding fail to stop attacks
Common security tactics like input filtering and blacklisting are ineffective against prompt injections due to the flexibility of natural language and encoding bypass techniques.
#7about 4 minutes
Using user confirmation and dual LLM models for defense
Advanced strategies include requiring user confirmation for sensitive actions or using a dual LLM architecture to isolate privileged operations from untrusted data processing.
#8about 5 minutes
The current state of LLM security and the need for awareness
There is currently no perfect solution for prompt injection, making developer awareness and careful design of LLM interactions the most critical defense.
Related jobs
Jobs that call for the skills explored in this talk.
Matching moments
04:10 MIN
Understanding the complexity of prompt injection attacks
Hacking AI - how attackers impose their will on AI
Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Upgrade to PRO for unlimited access to the full archive.
You have an account? Log in
01:43 MIN
Understanding and defending against prompt injection attacks
DevOps for AI: running LLMs in production with Kubernetes and KubeFlow
Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Upgrade to PRO for unlimited access to the full archive.
You have an account? Log in
04:58 MIN
Understanding and mitigating prompt injection attacks
Prompt Injection, Poisoning & More: The Dark Side of LLMs
Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Upgrade to PRO for unlimited access to the full archive.
You have an account? Log in
02:31 MIN
Understanding and defending against prompt injection attacks
Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails
Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Upgrade to PRO for unlimited access to the full archive.
You have an account? Log in
01:28 MIN
Understanding the security risk of prompt injection
The shadows that follow the AI generative models
Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Upgrade to PRO for unlimited access to the full archive.
You have an account? Log in
02:13 MIN
Key takeaways on prompt injection security
Manipulating The Machine: Prompt Injections And Counter Measures
Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Upgrade to PRO for unlimited access to the full archive.
You have an account? Log in
05:59 MIN
Understanding and demonstrating prompt injection attacks
The AI Security Survival Guide: Practical Advice for Stressed-Out Developers
Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Upgrade to PRO for unlimited access to the full archive.
You have an account? Log in
01:48 MIN
Strategies for mitigating prompt injection vulnerabilities
The AI Security Survival Guide: Practical Advice for Stressed-Out Developers
Unlock Moments
Create a free account to watch a limited number of Moments each month.
Upgrade to PRO for unlimited access to the full archive.
Upgrade to PRO for unlimited access to the full archive.
You have an account? Log in
Featured Partners
Related Videos
27:10Manipulating The Machine: Prompt Injections And Counter Measures
Georg Dresler
24:23A hundred ways to wreck your AI - the (in)security of machine learning systems
Balázs Kiss
31:19Skynet wants your Passwords! The Role of AI in Automating Social Engineering
Wolfgang Ettlinger & Alexander Hurbean
23:24Prompt Injection, Poisoning & More: The Dark Side of LLMs
Keno Dreßel
29:47You click, you lose: a practical look at VSCode's security
Thomas Chauchefoin & Paul Gerste
27:19Machine Learning: Promising, but Perilous
Nura Kawa
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
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.
GULP Information Services GmbH
GIT
Next.js
TypeScript
AWS Lambda
Amazon DynamoDB
+1
brandung GmbH & Co. KG
Intermediate
MongoDB
Next.js
GraphQL
PostgreSQL
TypeScript
+1