paper-with-me

Papers

Benchmarking the Robustness of Quantized Models

2023-04-08 · Yisong Xiao, Tianyuan Zhang, Shunchang Liu, Haotong Qin

Quantization has emerged as an essential technique for deploying deep neural networks (DNNs) on devices with limited resources. However, quantized models exhibit vulnerabilities when exposed to various noises in real-world applications. Despite the importance of evaluating the impact of quantization on robustness, existing research on this topic is limited and often disregards established principles of robustness evaluation, resulting in incomplete and inconclusive findings. To address this gap, we thoroughly evaluated the robustness of quantized models against various noises (adversarial attacks, natural corruptions, and systematic noises) on ImageNet. Extensive experiments demonstrate that lower-bit quantization is more resilient to adversarial attacks but is more susceptible to natural corruptions and systematic noises. Notably, our investigation reveals that impulse noise (in natural corruptions) and the nearest neighbor interpolation (in systematic noises) have the most significant impact on quantized models. Our research contributes to advancing the robust quantization of models and their deployment in real-world scenarios.

📄 PDF Abstract BibTeX arXiv:2304.03968

Code (0)

등록된 구현이 없습니다.

Tasks

BenchmarkingQuantization

Similar Papers 제목 키워드 기반

RobustMQ: Benchmarking Robustness of Quantized Models

2023-08-04 · Yisong Xiao, Aishan Liu, Tianyuan Zhang, Haotong Qin 외

Quantization has emerged as an essential technique for deploying deep neural networks (DNNs) on devices with limited resources. However, quantized models exhibit vulnerabilities when exposed to various noises in real-wor…

Adversarial RobustnessBenchmarkingQuantization

Improving the Robustness of Quantized Deep Neural Networks to White-Box Attacks using Stochastic Quantization and Information-Theoretic Ensemble Training

2023-11-30 · Saurabh Farkya, Aswin Raghavan, Avi Ziskind

Most real-world applications that employ deep neural networks (DNNs) quantize them to low precision to reduce the compute needs. We present a method to improve the robustness of quantized DNNs to white-box adversarial at…

DiversityInformation PlaneQuantization

Improved Gradient based Adversarial Attacks for Quantized Networks

2020-03-30 · Kartik Gupta, Thalaiyasingam Ajanthan

Neural network quantization has become increasingly popular due to efficient memory consumption and faster computation resulting from bitwise operations on the quantized networks. Even though they exhibit excellent gener…

image-classificationImage ClassificationQuantization

Phishing Detection in the Gen-AI Era: Quantized LLMs vs Classical Models

2025-07-10 · Jikesh Thapa, Gurrehmat Chahal, Serban Voinea Gabreanu, Yazan Otoum arxiv

Phishing attacks are becoming increasingly sophisticated, underscoring the need for detection systems that strike a balance between high accuracy and computational efficiency. This paper presents a comparative evaluation…

Computational EfficiencyAdversarial Robustness

DivQAT: Enhancing Robustness of Quantized Convolutional Neural Networks against Model Extraction Attacks

2025-12-30 · Kacem Khaled, Felipe Gohring de Magalhães, Gabriela Nicolescu arxiv

Convolutional Neural Networks (CNNs) and their quantized counterparts are vulnerable to extraction attacks, posing a significant threat of IP theft. Yet, the robustness of quantized models against these attacks is little…

Model extraction