RomilCyber commited on
Commit
67b1f3a
·
verified ·
1 Parent(s): d6335e1

Embed explainer video

Browse files
Files changed (1) hide show
  1. README.md +7 -1
README.md CHANGED
@@ -14,7 +14,13 @@ tags:
14
 
15
  ![PHANTOM DFIR: an agent that investigates, and a layer that keeps it honest](https://huggingface.co/RomilCyber/phantom-dfir-writeup/resolve/main/figures/cover.png)
16
 
17
- ## Tl;dr
 
 
 
 
 
 
18
 
19
  PHANTOM DFIR is a multi-agent forensic system. We attacked its own verifier with adversarial evidence, found three weaknesses, repaired them with a grounded verifier, and then chained **CuratorKIT, AlignTune and AuditKIT** around Cohere's **tiny-aya-global** to see whether a small open model can learn the verifier's job.
20
 
 
14
 
15
  ![PHANTOM DFIR: an agent that investigates, and a layer that keeps it honest](https://huggingface.co/RomilCyber/phantom-dfir-writeup/resolve/main/figures/cover.png)
16
 
17
+ **Watch how it works (1 min 41 s, with narration):**
18
+
19
+ <video controls preload="metadata" width="100%" src="https://huggingface.co/RomilCyber/phantom-dfir-writeup/resolve/main/phantom-dfir-how-it-works.mp4"></video>
20
+
21
+ [Open the video in a new tab](https://huggingface.co/RomilCyber/phantom-dfir-writeup/resolve/main/phantom-dfir-how-it-works.mp4)
22
+
23
+ ## Summary (TL;DR)
24
 
25
  PHANTOM DFIR is a multi-agent forensic system. We attacked its own verifier with adversarial evidence, found three weaknesses, repaired them with a grounded verifier, and then chained **CuratorKIT, AlignTune and AuditKIT** around Cohere's **tiny-aya-global** to see whether a small open model can learn the verifier's job.
26