Quantized models remain vulnerable to privacy attacks
Practical quantization levels have limited impact on membership privacy risks.
Quantization is a technique used to reduce model size for efficient deployment of large-scale deep neural networks (DNNs).
Practical quantization levels of - bits leave quantized models largely as vulnerable to membership inference attacks (MIAs) as full-precision counterparts.
Aggressive low-bit quantization like -bit can provide meaningful privacy gains, but this comes at the cost of substantial utility degradation.
Membership inference attacks (MIAs) are used to evaluate training data privacy risks.
Quantization is a technique for reducing model size.
The study evaluated eight state-of-the-art MIA attacks across six representative quantization methods.
Key facts
- Quantized models at - bits remain largely as vulnerable to membership inference attacks (MIAs) as full-precision models.
- Low-bit quantization of -bit can provide privacy gains but causes substantial utility degradation.
- Existing privacy defenses for full-precision DNNs provide limited protection for quantized models and increase utility degradation.