Skip to content
Hacking AI applications: In the trenches with DSPy
bugcrowd.com | blog | #ai-security | #red-teaming | #prompt-injection | #llm | #bugcrowd | #ai-red-teaming | #dspy
Summary
AI security researcher Ads Dawson demonstrates red teaming LLM applications with the DSPy framework, distinguishing AI red teaming from AI application security and probing business-logic flaws.
- Published
- Collected