Evolutionary Convolutional Neural Networks Using ABC

Zhu, Wenbo; Yeh, Wei-Chang; Chen, Jianwen; Da-feng, Chen; Li, Aiyuan; Lin, Yangyang

doi:10.1145/3318299.3318301

Cited by 39 publications

(26 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The hyperparameters of the CNN were tuned by the artificial bee colony optimization (ABC) in (Zhu et al, 2019). The ABC algorithm was used to set values for 13 CNN hyperparameters.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Classification methods for handwritten digit recognition: A survey

Tuba¹,

Tuba²,

Veinović³

2023

Vojnotehnički glasnik

View full text Add to dashboard Cite

Introduction/purpose: This paper provides a survey of handwritten digit recognition methods tested on the MNIST dataset. Methods: The paper analyzes, synthesizes and compares the development of different classifiers applied to the handwritten digit recognition problem, from linear classifiers to convolutional neural networks. Results: Handwritten digit recognition classification accuracy tested on the MNIST dataset while using training and testing sets is now higher than 99.5% and the most successful method is a convolutional neural network. Conclusions: Handwritten digit recognition is a problem with numerous real-life applications. Accurate recognition of various handwriting styles, specifically digits is a task studied for decades and this paper summarizes the achieved results. The best results have been achieved with convolutional neural networks while the worst methods are linear classifiers. The convolutional neural networks give better results if the dataset is expended with data augmentation.

show abstract

“…The hyperparameters of the CNN were tuned by the artificial bee colony optimization (ABC) in (Zhu et al, 2019). The ABC algorithm was used to set values for 13 CNN hyperparameters.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Classification methods for handwritten digit recognition: A survey

Tuba¹,

Tuba²,

Veinović³

2023

Vojnotehnički glasnik

View full text Add to dashboard Cite

show abstract

“…This focuses on the area includes the robustification of Deep RL algorithms against poisoning and evasion attacks that aim to attack the algorithmic functionalities of the automated agent. While very low number of publications have focused on such attacks for Deep RL algorithms, it is evident that the future cyber attackers will implement such attacks in the future through Deep RL and neural network based research within other domains [14,26,108,130]. If this challenge is not addressed, future networked systems could be vulnerable to algorithmic attacks that could potentially take control of the automated blue agent, and eventually the entire network.…”

Section: Challenges and Their Importancementioning

confidence: 99%

Automated Cyber Defence: A Review

Vyas¹,

Hannay²,

Bolton³

et al. 2023

Preprint

View full text Add to dashboard Cite

Within recent times, cybercriminals have curated a variety of organised and resolute cyber attacks within a range of cyber systems, leading to consequential ramifications to private and governmental institutions. Current security-based automation and orchestrations focus on automating fixed purpose and hard-coded solutions, which are easily surpassed by modern-day cyber attacks. Research within Automated Cyber Defence will allow the development and enabling intelligence response by autonomously defending networked systems through sequential decision-making agents. This article comprehensively elaborates the developments within Automated Cyber Defence through a requirement analysis divided into two sub-areas, namely, automated defence and attack agents and Autonomous Cyber Operation (ACO) Gyms. The requirement analysis allows the comparison of automated agents and highlights the importance of ACO Gyms for their continual development. The requirement analysis is also used to critique ACO Gyms with an overall aim to develop them for deploying automated agents within real-world networked systems. Relevant future challenges were addressed from the overall analysis to accelerate development within the area of Automated Cyber Defence.

show abstract

“…Advanced Attacks. We do not evaluate all types of targeted attacks, such as subpopulation attacks [34], triggerless poisoning attacks [2,32,91] that do not require modifying the image during inference, other code poisoning attacks [29,88] or against natural backdoors [81,83]. Further research is necessary to validate the effectiveness of the surveyed defenses against these attacks.…”

Section: Oursmentioning

confidence: 99%

SoK: How Robust is Image Classification Deep Neural Network Watermarking?

Lukas

Jiang

et al. 2022

2022 IEEE Symposium on Security and Privacy (SP)

View full text Add to dashboard Cite

Deep image classification models trained on large amounts of webscraped data are vulnerable to data poisoning, a mechanism for backdooring models. Even a few poisoned samples seen during training can entirely undermine the model's integrity during inference. While it is known that poisoning more samples enhances an attack's effectiveness and robustness, it is unknown whether poisoning too many samples weakens an attack by making it more detectable. We observe a fundamental detectability/robustness tradeoff in data poisoning attacks: Poisoning too few samples renders an attack ineffective and not robust, but poisoning too many samples makes it detectable. This raises the bar for data poisoning attackers who have to balance this trade-off to remain robust and undetectable. Our work proposes two defenses designed to (i) detect and (ii) repair poisoned models as a post-processing step after training using a limited amount of trusted image-label pairs. We show that our defenses mitigate all surveyed attacks and outperform existing defenses using less trusted data to repair a model. Our defense scales to joint vision-language models, such as CLIP, and interestingly, we find that attacks on larger models are more easily detectable but also more robust than those on smaller models. Lastly, we propose two adaptive attacks demonstrating that while our work raises the bar for data poisoning attacks, it cannot mitigate all forms of backdooring. CCS CONCEPTS• Security and privacy → Software and application security; • Computing methodologies → Machine learning.

show abstract

Evolutionary Convolutional Neural Networks Using ABC

Cited by 39 publications

References 18 publications

Classification methods for handwritten digit recognition: A survey

Classification methods for handwritten digit recognition: A survey

Automated Cyber Defence: A Review

SoK: How Robust is Image Classification Deep Neural Network Watermarking?

Contact Info

Product

Resources

About