Neural Network Security: Hiding CNN Parameters with Guided Grad-CAM

Guiga, Linda; Roscoe, A. W.

doi:10.5220/0009061206110618

Cited by 4 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Traditionally, AI is regarded as a "black box," which impairs its widespread usage, e.g., the black box properties of traditional AI are problematic for the FDA. Nevertheless, with the help of explainability of modern AI techniques [35], the radiologist and patients will gain confidence in our proposed AI model, as the heatmap provides a clear and understandable interpretation of how AI predicts COVID-19 and other chest infectious disease from healthy subjects, which was also stated in reference [36]. Many new AI-based anatomic pathological systems now pass through FDA approval, such as whole slide images (WSI) [37], since the doctors know the relationships between the diagnosis and the explained answer.…”

Section: 3mentioning

confidence: 99%

PSSPNN: PatchShuffle Stochastic Pooling Neural Network for an Explainable Diagnosis of COVID-19 with Multiple-Way Data Augmentation

Wang

Zhang

Cheng

et al. 2021

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Aim. COVID-19 has caused large death tolls all over the world. Accurate diagnosis is of significant importance for early treatment. Methods. In this study, we proposed a novel PSSPNN model for classification between COVID-19, secondary pulmonary tuberculosis, community-captured pneumonia, and healthy subjects. PSSPNN entails five improvements: we first proposed the n-conv stochastic pooling module. Second, a novel stochastic pooling neural network was proposed. Third, PatchShuffle was introduced as a regularization term. Fourth, an improved multiple-way data augmentation was used. Fifth, Grad-CAM was utilized to interpret our AI model. Results. The 10 runs with random seed on the test set showed our algorithm achieved a microaveraged F1 score of 95.79%. Moreover, our method is better than nine state-of-the-art approaches. Conclusion. This proposed PSSPNN will help assist radiologists to make diagnosis more quickly and accurately on COVID-19 cases.

show abstract

Section: 3mentioning

confidence: 99%

PSSPNN: PatchShuffle Stochastic Pooling Neural Network for an Explainable Diagnosis of COVID-19 with Multiple-Way Data Augmentation

Wang

Zhang

Cheng

et al. 2021

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

show abstract

“…Guiga and Roscoe [98] explored input perturbation for image data. They picked unimportant pixels using the Gradient-weighted Class Activation Mapping (Grad-CAM) method [105], and added noise to these.…”

Section: Data Perturbationmentioning

confidence: 99%

“…A mark ↘means that a defence is partially effective: either the attack performance has fallen only slightly (less than 5%), (PRADA) [8] (distill.) [48] (parasatic) [102] No transfer learning [5,11] WM (DAWN) [94] Input [98] Output [99] Output + monitor [100] Output (MAD) [9] (BDPL) [75] + Monitor (MDP) [13] Witn. Finding [1,20,52] ✓[75] ESA-P [1,52] ✗[1] ✗ [52] ∼ ✓ [98] ✓[13] ESA-P (dupl.…”

Section: Analysis Of Attacks and Defencesmentioning

confidence: 99%

See 1 more Smart Citation

I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences

Oliynyk¹,

Mayer²,

Rauber³

2022

Preprint

View full text Add to dashboard Cite

Machine Learning-as-a-Service (MLaaS) has become a widespread paradigm, making even the most complex machine learning models available for clients via e.g. a pay-per-query principle. This allows users to avoid time-consuming processes of data collection, hyperparameter tuning, and model training. However, by giving their customers access to the (predictions of their) models, MLaaS providers endanger their intellectual property, such as sensitive training data, optimised hyperparameters, or learned model parameters.Adversaries can create a copy of the model with (almost) identical behavior using the the prediction labels only. While many variants of this attack have been described, only scattered defence strategies have been proposed, addressing isolated threats. This raises the necessity for a thorough systematisation of the field of model stealing, to arrive at a comprehensive understanding why these attacks are successful, and how they could be holistically defended against. We address this by categorising and comparing model stealing attacks, assessing their performance, and exploring corresponding defence techniques in different settings. We propose a taxonomy for attack and defence approaches, and provide guidelines on how to select the right attack or defence strategy based on the goal and available resources. Finally, we analyse which defences are rendered less effective by current attack strategies.CCS Concepts: • Security and privacy → Vulnerability management; • Computing methodologies → Machine learning.

show abstract

Research on Network Security Authentication Method Based on Data Mining Technology

Wang

2022

IoT and Big Data Technologies for Health Care

View full text Add to dashboard Cite

Neural Network Security: Hiding CNN Parameters with Guided Grad-CAM

Cited by 4 publications

References 0 publications

PSSPNN: PatchShuffle Stochastic Pooling Neural Network for an Explainable Diagnosis of COVID-19 with Multiple-Way Data Augmentation

PSSPNN: PatchShuffle Stochastic Pooling Neural Network for an Explainable Diagnosis of COVID-19 with Multiple-Way Data Augmentation

I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences

Research on Network Security Authentication Method Based on Data Mining Technology

Contact Info

Product

Resources

About