Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
amarck
/
heap-trm
like
0
security
heap-exploitation
deserialization
tiny-recursive-model
ctf
exploit-detection
action-prediction
arxiv:
2510.04871
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
heap-trm
/
bench
45.3 kB
Ctrl+K
Ctrl+K
1 contributor
History:
2 commits
amarck
Defensible benchmark: heaptrm 65% vs blind 32% same-session
e1fab24
3 months ago
observe_once_benchmark.py
Safe
10.8 kB
Benchmark results: observe-once fails (stale addresses across processes)
3 months ago
observe_once_results.json
Safe
3.42 kB
Benchmark results: observe-once fails (stale addresses across processes)
3 months ago
results.json
Safe
3.96 kB
Benchmark results: observe-once fails (stale addresses across processes)
3 months ago
run_llm_benchmark.py
Safe
15.1 kB
Benchmark results: observe-once fails (stale addresses across processes)
3 months ago
same_session_benchmark.py
Safe
8.04 kB
Defensible benchmark: heaptrm 65% vs blind 32% same-session
3 months ago
same_session_results.json
Safe
3.99 kB
Defensible benchmark: heaptrm 65% vs blind 32% same-session
3 months ago