Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Rogue Agents - Stop AI from misusing APIs
Search
Dominik Kundel
PRO
January 23, 2024
Programming
0
250
Rogue Agents - Stop AI from misusing APIs
Dominik Kundel
PRO
January 23, 2024
Tweet
Share
More Decks by Dominik Kundel
See All by Dominik Kundel
AWS re:Invent '24 - Rogue Agents - Stop AI from misusing APIs
dkundel
PRO
0
44
AI for Marketers Sept '24 - How AI Agents will change your
dkundel
PRO
0
240
AGI Builders July '24 - Rogue Agents - Stop AI from misusing APIs
dkundel
PRO
0
190
AI Engineer World's Fair '24 - Cooking with Fire without
dkundel
PRO
0
200
SIGNAL 2021 - Live Developer Mode
dkundel
PRO
0
170
OpenJS World - What the AST?
dkundel
PRO
0
460
WFHConf - Move to TypeScript at your own Pace
dkundel
PRO
0
320
SFNode '20 - How to move your project to TypeScript
dkundel
PRO
0
330
Node+JS Interactive '19 - When Porgs Scream at Webpack and Other Stories
dkundel
PRO
0
360
Other Decks in Programming
See All in Programming
PHPUnitの限界をPlaywrightで補完するテストアプローチ
yuzneri
0
370
「次に何を学べばいいか分からない」あなたへ──若手エンジニアのための学習地図
panda_program
3
710
Dart 参戦!!静的型付き言語界の隠れた実力者
kno3a87
0
160
Streamlitで実現できるようになったこと、実現してくれたこと
ayumu_yamaguchi
2
270
kiroでゲームを作ってみた
iriikeita
0
140
抽象化という思考のツール - 理解と活用 - / Abstraction-as-a-Tool-for-Thinking
shin1x1
1
920
decksh - a little language for decks
ajstarks
4
21k
Bedrock AgentCore ObservabilityによるAIエージェントの運用
licux
8
550
プロダクトという一杯を作る - プロダクトチームが味の責任を持つまでの煮込み奮闘記
hiliteeternal
0
370
[Codecon - 2025] Como não odiar seus testes
camilacampos
0
100
AWS Summit Japan 2024と2025の比較/はじめてのKiro、今あなたは岐路に立つ
satoshi256kbyte
1
260
バイブコーディング超えてバイブデプロイ〜CloudflareMCPで実現する、未来のアプリケーションデリバリー〜
azukiazusa1
3
770
Featured
See All Featured
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
48
2.9k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
47
9.6k
Designing for Performance
lara
610
69k
Keith and Marios Guide to Fast Websites
keithpitt
411
22k
Unsuck your backbone
ammeep
671
58k
Improving Core Web Vitals using Speculation Rules API
sergeychernyshev
18
1k
GraphQLの誤解/rethinking-graphql
sonatard
71
11k
Fireside Chat
paigeccino
37
3.6k
Building a Scalable Design System with Sketch
lauravandoore
462
33k
The Power of CSS Pseudo Elements
geoffreycrofte
77
5.9k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
130
19k
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
31
1.3k
Transcript
Rogue Agents Stop AI from misusing APIs TechTalks SF -
Jan ‘24 Dominik Kundel d-k.im/rogue-agents Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
console.log(` Hi! I’m Dominik Kundel `); dkundel.com @dkundel
[email protected]
github/dkundel
Product Lead @ Twilio && JavaScript Hacker Dominik Kundel | @dkundel
How can we have AI interact with APIs? Dominik Kundel
| @dkundel
How can we have AI safely interact with APIs? Dominik
Kundel | @dkundel
How can we have AI interact with APIs? Dominik Kundel
| @dkundel
Dominik Kundel | @dkundel How to connect AI to APIs
Platforms Frameworks Native LLM Functions 🦜🔗
Dominik Kundel | @dkundel Platforms Frameworks Native LLM Functions 🦜🔗
Source: LangChain Documentation
Dominik Kundel | @dkundel Platforms Frameworks Native LLM Functions 🦜🔗
Source: LangChain Documentation
What’s the problem? Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
Unpredictable Dominik Kundel | @dkundel
Dominik Kundel | @dkundel Easily Impressionable
Dominik Kundel | @dkundel Source: Simon Willison - Prompt Injections:
what’s the worst that can happen?
Dominik Kundel | @dkundel Source: Simon Willison - Prompt Injections:
what’s the worst that can happen?
Dominik Kundel | @dkundel Source: Simon Willison - Prompt Injections:
what’s the worst that can happen?
Dominik Kundel | @dkundel Rules are “suggestions”
Dominik Kundel | @dkundel Source: Simon Willison - Prompt injections
explained
Dominik Kundel | @dkundel Source: Simon Willison - Prompt injections
explained
Dominik Kundel | @dkundel The problems with LLMs Unpredictable Easily
Impressionable Rules “suggestions”
Dominik Kundel | @dkundel
How do we “LLM-proof” our APIs? Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
Dominik Kundel | @dkundel LLM
Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
Dominik Kundel | @dkundel
Dominik Kundel | @dkundel LLM
What security measures? Dominik Kundel | @dkundel
Dominik Kundel | @dkundel Security Measures
Dominik Kundel | @dkundel Security Measures Data Validation
Dominik Kundel | @dkundel Security Measures Data Validation Rate Limiting
Dominik Kundel | @dkundel Security Measures Data Validation Authentication Rate
Limiting
Dominik Kundel | @dkundel Security Measures
Dominik Kundel | @dkundel Security Measures Authorization
Dominik Kundel | @dkundel Security Measures Authorization Least Privilege
Dominik Kundel | @dkundel Security Measures Authorization Eliminate con fi
dential & unnecessary data Least Privilege
Dominik Kundel | @dkundel Do threat modeling!
Dominik Kundel | @dkundel Takeaways?
Treat AI-exposed APIs as public Dominik Kundel | @dkundel Takeaways?
Treat AI-exposed APIs as public Security mechanisms outside AI world
Dominik Kundel | @dkundel Takeaways?
Treat AI-exposed APIs as public Security mechanisms outside AI world
Dominik Kundel | @dkundel Takeaways? Toddler-proof your home API!
console.log(` 💖 Thank You! 🎉 `); dkundel.com @dkundel
[email protected]
github/dkundel
d-k.im/rogue-agents Dominik Kundel | @dkundel | #workfromhomeconf |