Hugging Face's logo

salvepilo
/
llama-cpp-strlen-oob-poc

GGUF
Model card Files
xet
 Community

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Heap Buffer Over-Read via strlen() on Unterminated Precompiled Charsmap

PoC for heap buffer over-read in llama.cpp UGM (T5) tokenizer.

Files

  • poc_strlen_oob.gguf - Crafted GGUF model
  • poc_strlen_oob.py - Generator script

Disclaimer

For security research and responsible disclosure only.

Downloads last month
-
GGUF
Model size
0 params
Architecture
t5
Hardware compatibility
Log In to add your hardware

We're not able to determine the quantization variants.

View all variants
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support