Position: Certified Robustness Does Not (Yet) Imply Model Security
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916889404375040 |
|---|---|
| author | Cullen, Andrew C. Montague, Paul Erfani, Sarah M. Rubinstein, Benjamin I. P. |
| author_facet | Cullen, Andrew C. Montague, Paul Erfani, Sarah M. Rubinstein, Benjamin I. P. |
| contents | While certified robustness is widely promoted as a solution to adversarial examples in Artificial Intelligence systems, significant challenges remain before these techniques can be meaningfully deployed in real-world applications. We identify critical gaps in current research, including the paradox of detection without distinction, the lack of clear criteria for practitioners to evaluate certification schemes, and the potential security risks arising from users' expectations surrounding ``guaranteed" robustness claims. These create an alignment issue between how certifications are presented and perceived, relative to their actual capabilities. This position paper is a call to arms for the certification research community, proposing concrete steps to address these fundamental challenges and advance the field toward practical applicability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_13024 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Position: Certified Robustness Does Not (Yet) Imply Model Security Cullen, Andrew C. Montague, Paul Erfani, Sarah M. Rubinstein, Benjamin I. P. Cryptography and Security Machine Learning While certified robustness is widely promoted as a solution to adversarial examples in Artificial Intelligence systems, significant challenges remain before these techniques can be meaningfully deployed in real-world applications. We identify critical gaps in current research, including the paradox of detection without distinction, the lack of clear criteria for practitioners to evaluate certification schemes, and the potential security risks arising from users' expectations surrounding ``guaranteed" robustness claims. These create an alignment issue between how certifications are presented and perceived, relative to their actual capabilities. This position paper is a call to arms for the certification research community, proposing concrete steps to address these fundamental challenges and advance the field toward practical applicability. |
| title | Position: Certified Robustness Does Not (Yet) Imply Model Security |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2506.13024 |