tavialiu nielsr HF Staff commited on
Commit
1935bbf
·
1 Parent(s): 550e8cf

Add pipeline tag and link to paper (#1)

Browse files

- Add pipeline tag and link to paper (b6835e8158e6d5c8848cef7e9e7d7e85fdde31ee)


Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +7 -4
README.md CHANGED
@@ -1,18 +1,21 @@
1
  ---
2
- license: mit
 
3
  language:
4
  - en
 
 
5
  tags:
6
  - prompt-injection
7
  - indirect-prompt-injection
8
  - agent-security
9
  - agentdojo
10
- datasets:
11
- - tavialiu/CAD-data
12
  ---
13
 
14
  # CAD Models
15
 
 
 
16
  Classifier checkpoints for CAD, from *Robust Context-Aware Detection of Malicious Instructions
17
  in Text* (Liu, Ma, and Vorobeychik, 2026).
18
 
@@ -57,4 +60,4 @@ bash scripts/run_agentdojo_benchmark.sh banking slack travel
57
  journal = {arXiv preprint},
58
  year = {2026}
59
  }
60
- ```
 
1
  ---
2
+ datasets:
3
+ - tavialiu/CAD-data
4
  language:
5
  - en
6
+ license: mit
7
+ pipeline_tag: text-classification
8
  tags:
9
  - prompt-injection
10
  - indirect-prompt-injection
11
  - agent-security
12
  - agentdojo
 
 
13
  ---
14
 
15
  # CAD Models
16
 
17
+ Paper: [Robust Context-Aware Detection of Malicious Instructions in Text](https://huggingface.co/papers/2608.05430)
18
+
19
  Classifier checkpoints for CAD, from *Robust Context-Aware Detection of Malicious Instructions
20
  in Text* (Liu, Ma, and Vorobeychik, 2026).
21
 
 
60
  journal = {arXiv preprint},
61
  year = {2026}
62
  }
63
+ ```