Impactful Bit-Flip Search on Full-precision Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912233942941696 |
|---|---|
| author | Benedek, Nadav Levy, Matan Sharif, Mahmood |
| author_facet | Benedek, Nadav Levy, Matan Sharif, Mahmood |
| contents | Neural networks have shown remarkable performance in various tasks, yet they remain susceptible to subtle changes in their input or model parameters. One particularly impactful vulnerability arises through the Bit-Flip Attack (BFA), where flipping a small number of critical bits in a model's parameters can severely degrade its performance. A common technique for inducing bit flips in DRAM is the Row-Hammer attack, which exploits frequent uncached memory accesses to alter data. Identifying susceptible bits can be achieved through exhaustive search or progressive layer-by-layer analysis, especially in quantized networks. In this work, we introduce Impactful Bit-Flip Search (IBS), a novel method for efficiently pinpointing and flipping critical bits in full-precision networks. Additionally, we propose a Weight-Stealth technique that strategically modifies the model's parameters in a way that maintains the float values within the original distribution, thereby bypassing simple range checks often used in tamper detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_08133 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Impactful Bit-Flip Search on Full-precision Models Benedek, Nadav Levy, Matan Sharif, Mahmood Machine Learning Cryptography and Security Neural networks have shown remarkable performance in various tasks, yet they remain susceptible to subtle changes in their input or model parameters. One particularly impactful vulnerability arises through the Bit-Flip Attack (BFA), where flipping a small number of critical bits in a model's parameters can severely degrade its performance. A common technique for inducing bit flips in DRAM is the Row-Hammer attack, which exploits frequent uncached memory accesses to alter data. Identifying susceptible bits can be achieved through exhaustive search or progressive layer-by-layer analysis, especially in quantized networks. In this work, we introduce Impactful Bit-Flip Search (IBS), a novel method for efficiently pinpointing and flipping critical bits in full-precision networks. Additionally, we propose a Weight-Stealth technique that strategically modifies the model's parameters in a way that maintains the float values within the original distribution, thereby bypassing simple range checks often used in tamper detection. |
| title | Impactful Bit-Flip Search on Full-precision Models |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2411.08133 |