CalvinBackup/Awesome-model-inversion-attack
1
0
Fork 0
mirror of https://github.com/AndrewZhou924/Awesome-model-inversion-attack.git synced 2026-08-22 08:57:12 +02:00
Code Issues Packages Projects Releases Wiki Activity

Classify Magic Words as a related embedding attack

Browse Source
This commit is contained in:
AndrewZhou924
2026-08-08 12:36:28 +08:00
parent 6a7c0346b4
commit 747db98ee6
1 changed files with 6 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+6
View File
@@ -491,6 +491,12 @@ This historical list includes embedding inversion, prompt inversion, memorizatio
- [Blog 2020] Attacks against Machine Learning Privacy (Part 1): Model Inversion Attacks with the IBM-ART Framework [[blog]](https://franziska-boenisch.de/posts/2020/12/model-inversion/) - [Blog 2020] Attacks against Machine Learning Privacy (Part 1): Model Inversion Attacks with the IBM-ART Framework [[blog]](https://franziska-boenisch.de/posts/2020/12/model-inversion/)
- [Slides 2020] ML and DP [[slides]](https://www.cs.toronto.edu/~toni/Courses/Fairness/Lectures/ML-and-DP-v2.pdf) - [Slides 2020] ML and DP [[slides]](https://www.cs.toronto.edu/~toni/Courses/Fairness/Lectures/ML-and-DP-v2.pdf)
### Related representation-space attacks (not model inversion)
These papers affect interfaces also studied by model inversion research, but do not reconstruct private training information and are therefore listed separately.
- [arXiv 2025] (black- and white-box) **Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models.** Exploits embedding-distribution bias to find universal suffixes that manipulate cosine similarity and bypass embedding-based safeguards. [[paper]](https://arxiv.org/abs/2501.18280)
## Contributing ## Contributing
Contributions are welcome through pull requests or issues. Please use official publisher, proceedings, OpenReview, ACL Anthology, PMLR, CVF/ECVA, USENIX, DOI, or arXiv links whenever possible. Contributions are welcome through pull requests or issues. Please use official publisher, proceedings, OpenReview, ACL Anthology, PMLR, CVF/ECVA, USENIX, DOI, or arXiv links whenever possible.