• Recent & Upcoming Talks
    • Example Talk
  • Publications
    • Beyond Accuracy: Characterizing Code Comprehension Capabilities in (Large) Language Models
    • Coverage-Guided Multi-Agent Harness Generation for Java Library Fuzzing
    • DASA: Fully Gradient-based Program Analysis (Competition Contribution)
    • SWAT: Improvements to the symbolic executor (competition contribution)
    • Attacks and Remedies for Randomness in AI: Cryptanalysis of PHILOX and THREEFRY
    • AutoStub: Genetic Programming-Based Stub Creation for Symbolic Execution
    • Prompt Pirates Need a Map: Stealing Seeds helps Stealing Prompts
    • Trace Gadgets: Minimizing Code Context for Machine Learning-Based Vulnerability Prediction
    • OCEAN: Open-World Contrastive Authorship Identification
    • SWAT: Modular Dynamic Symbolic Execution for Java Applications using Dynamic Instrumentation (Competition Contribution)
    • Madvex: Instrumentation-Based Adversarial Attacks on Machine Learning Malware Detection
  • Projects
  • Blog
    • 🎉 Easily create your own simple yet highly customizable blog
    • 🧠 Sharpen your thinking with a second brain
    • 📈 Communicate your results effectively with the best data visualizations
    • 👩🏼‍🏫 Teach academic courses
    • ✅ Manage your projects
  • Projects
    • Pandas
    • PyTorch
    • scikit-learn
  • Experience
  • Teaching
    • Learn JavaScript
    • Learn Python

Prompt Pirates Need a Map: Stealing Seeds helps Stealing Prompts

Jan 1, 2025·
Felix Mächtle
,
Ashwath Shetty
,
Jonas Sander
,
Nils Loose
,
Sören Pirk
,
Thomas Eisenbarth
· 0 min read
Cite arXiv URL
Type
Manuscript
Last updated on Jan 1, 2025
← AutoStub: Genetic Programming-Based Stub Creation for Symbolic Execution Jan 1, 2025
Trace Gadgets: Minimizing Code Context for Machine Learning-Based Vulnerability Prediction Jan 1, 2025 →

© 2026 Me.

Published with Hugo Blox Builder — the free, open source website builder that empowers creators.