Exploiting Leaderboards for Large-Scale Distribution of Malicious Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916840218820608 |
|---|---|
| author | Suri, Anshuman Chaudhari, Harsh Peng, Yuefeng Naseh, Ali Houmansadr, Amir Oprea, Alina |
| author_facet | Suri, Anshuman Chaudhari, Harsh Peng, Yuefeng Naseh, Ali Houmansadr, Amir Oprea, Alina |
| contents | While poisoning attacks on machine learning models have been extensively studied, the mechanisms by which adversaries can distribute poisoned models at scale remain largely unexplored. In this paper, we shed light on how model leaderboards -- ranked platforms for model discovery and evaluation -- can serve as a powerful channel for adversaries for stealthy large-scale distribution of poisoned models. We present TrojanClimb, a general framework that enables injection of malicious behaviors while maintaining competitive leaderboard performance. We demonstrate its effectiveness across four diverse modalities: text-embedding, text-generation, text-to-speech and text-to-image, showing that adversaries can successfully achieve high leaderboard rankings while embedding arbitrary harmful functionalities, from backdoors to bias injection. Our findings reveal a significant vulnerability in the machine learning ecosystem, highlighting the urgent need to redesign leaderboard evaluation mechanisms to detect and filter malicious (e.g., poisoned) models, while exposing broader security implications for the machine learning community regarding the risks of adopting models from unverified sources. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_08983 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploiting Leaderboards for Large-Scale Distribution of Malicious Models Suri, Anshuman Chaudhari, Harsh Peng, Yuefeng Naseh, Ali Houmansadr, Amir Oprea, Alina Machine Learning Cryptography and Security While poisoning attacks on machine learning models have been extensively studied, the mechanisms by which adversaries can distribute poisoned models at scale remain largely unexplored. In this paper, we shed light on how model leaderboards -- ranked platforms for model discovery and evaluation -- can serve as a powerful channel for adversaries for stealthy large-scale distribution of poisoned models. We present TrojanClimb, a general framework that enables injection of malicious behaviors while maintaining competitive leaderboard performance. We demonstrate its effectiveness across four diverse modalities: text-embedding, text-generation, text-to-speech and text-to-image, showing that adversaries can successfully achieve high leaderboard rankings while embedding arbitrary harmful functionalities, from backdoors to bias injection. Our findings reveal a significant vulnerability in the machine learning ecosystem, highlighting the urgent need to redesign leaderboard evaluation mechanisms to detect and filter malicious (e.g., poisoned) models, while exposing broader security implications for the machine learning community regarding the risks of adopting models from unverified sources. |
| title | Exploiting Leaderboards for Large-Scale Distribution of Malicious Models |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2507.08983 |