2 points | by HieronymusBosch 11 hours ago ago
1 comments
From the paper [0], they're using a specialized model structure, so at least they are not part of the LLM hype. That's good. But I still wonder how this compares to existing rule- and manual heuristics-based approaches like github/linguist.
[0]: https://securityresearch.google/magika/2025_icse_magika.pdf
From the paper [0], they're using a specialized model structure, so at least they are not part of the LLM hype. That's good. But I still wonder how this compares to existing rule- and manual heuristics-based approaches like github/linguist.
[0]: https://securityresearch.google/magika/2025_icse_magika.pdf