Keno Dreßel
Prompt Injection, Poisoning & More: The Dark Side of LLMs
#1about 5 minutes
Understanding and mitigating prompt injection attacks
Prompt injection manipulates LLM outputs through direct or indirect methods, requiring mitigations like restricting model capabilities and applying guardrails.
#2about 6 minutes
Protecting against data and model poisoning risks
Malicious or biased training data can poison a model's worldview, necessitating careful data screening and keeping models up-to-date.
#3about 6 minutes
Securing downstream systems from insecure model outputs
LLM outputs can exploit downstream systems like databases or frontends, so they must be treated as untrusted user input and sanitized accordingly.
#4about 4 minutes
Preventing sensitive information disclosure via LLMs
Sensitive data used for training can be extracted from models, highlighting the need to redact or anonymize information before it reaches the LLM.
#5about 1 minute
Why comprehensive security is non-negotiable for LLMs
Just like in traditional application security, achieving 99% security is still a failing grade because attackers will find and exploit any existing vulnerability.
Related jobs
Jobs that call for the skills explored in this talk.
Matching moments
04:49 MIN
The current state of LLM security and the need for awareness
ChatGPT, ignore the above instructions! Prompt injection attacks and how to avoid them.
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
01:37 MIN
Understanding the security risks of AI integrations
Three years of putting LLMs into Software - Lessons learned
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
04:10 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
01:48 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
03:43 MIN
AI privacy concerns and prompt engineering
Coffee with Developers - Cassidy Williams -
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
03:19 MIN
The overlooked security risks of AI and LLMs
WeAreDevelopers LIVE - Chrome for Sale? Comet - the upcoming perplexity browser Stealing and leaking
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
27:32ChatGPT, ignore the above instructions! Prompt injection attacks and how to avoid them.
Sebastian Schrittwieser
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
26:30Three years of putting LLMs into Software - Lessons learned
Simon A.T. Jiménez
31:12Using LLMs in your Product
Daniel Töws
23:50Data Privacy in LLMs: Challenges and Best Practices
Aditi Godbole
35:37Can Machines Dream of Secure Code? Emerging AI Security Risks in LLM-driven Developer Tools
Liran Tal
Related Articles
View all articles
From learning to earning
Jobs that call for the skills explored in this talk.
MLL Münchner Leukämielabor GmbH