4,598 Reverse Engineering Benchmarks Released
dyn___ · x · 2026-07-13
Crackmes-One has released the **crackmes-RE** benchmark dataset: - A total of **4,598** crackmes - Each sample includes a flag and/or a runnable verifier script, with **2,172** featuring verifiers - Standardized labels for obfuscation, anti-debugging, and protection mechanisms are also included This dataset aims to evaluate the reverse engineering capabilities of **LLMs** and **decompilers**.
More from Research
- Knowledgeless Language Models cut closed-book recall by anonymizing entities during pretraining — gdm3000 · 2026-07-21
- CPU-native LLM pilot passes 4 of 5 gates, but cross-tokenizer distillation still loses — WildPino25 · 2026-07-21
- A GPT 5.6 Sol workflow reportedly generates an infinite family of counterexamples — OwariDa · 2026-07-21
- A research guide v7 surfaces two contradictions instead of smoothing them over — Fantastic_Aside6599 · 2026-07-21
- Agents can remember facts, but still forget how to do the job — No_Advertising2536 · 2026-07-21
- AI-assisted search finds small counterexamples to the Gaussian Moments Conjecture — RichmanRonald · 2026-07-21