Using FGSM Targeted Attack to Improve the Transferability of Adversarial Example

Xu, Jin; Cai, Zhendong; Shen, Wei

doi:10.1109/icece48499.2019.9058535

Cited by 12 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where is the magnitude. Details of studies on FGSMA on image domain and countering some of the shortcomings of the can be found in [27], [28], [29], [52], [53], and [54] 2) JSMA Papenot proposed JSMA to address the problem of FGSMA by reducing the scale of perturbation through the iterative computation of the best feature to perturb for misclassification [55]. This approach enables the extraction of the influence of an individual feature on a particular class through a saliency map.…”

Section: ) Fgsmamentioning

confidence: 99%

Statistical Detection of Adversarial Examples in Blockchain-Based Federated Forest In-Vehicle Network Intrusion Detection Systems

et al. 2022

View full text Add to dashboard Cite

The internet-of-Vehicle (IoV) can facilitate seamless connectivity between connected vehicles (CV), autonomous vehicles (AV), and other IoV entities. Intrusion Detection Systems (IDSs) for IoV networks can rely on machine learning (ML) to protect the in-vehicle network from cyber-attacks. Blockchainbased Federated Forests (BFFs) could be used to train ML models based on data from IoV entities while protecting the confidentiality of the data and reducing the risks of tampering with the data. However, ML models are still vulnerable to evasion, poisoning and exploratory attacks by adversarial examples. The BFF-IDS offers partial defence against poisoning but has no measure for evasion attacks, the most common attack/threat faced by ML models. Besides, the impact of adversarial examples transferability in CAN IDS has largely remained untested. This paper investigates the impact of various possible adversarial examples on the BFF-IDS. We also investigated the statistical adversarial detector's effectiveness and resilience in detecting the attacks and subsequent countermeasures by augmenting the model with detected samples. Our investigation results established that BFF-IDS is very vulnerable to adversarial examples attacks. The statistical adversarial detector and the subsequent BFF-IDS augmentation (BFF-IDS(AUG)) provide an effective mechanism against the adversarial examples. Consequently, integrating the statistical adversarial detector and the subsequent BFF-IDS augmentation with the detected adversarial samples provides a sustainable security framework against adversarial examples and other unknown attacks. INDEX TERMSAdversarial examples, artificial intelligent (AI), blockchain, controller area network (CAN), federated learning, intrusion detection system (IDS).

show abstract

Section: ) Fgsmamentioning

confidence: 99%

Statistical Detection of Adversarial Examples in Blockchain-Based Federated Forest In-Vehicle Network Intrusion Detection Systems

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Using this matrix, a new adversarial image will be created which gets misclassified by the model. This can be summarised using the following expression as shown in eqn 1 [15]:…”

Section: Literature Surveymentioning

confidence: 99%

Facial Privacy Preservation using FGSM and Universal Perturbation attacks

Nishchal¹

2022

Preprint

View full text Add to dashboard Cite

<p>Recent research has established the possibility of deducing soft-biometric attributes such as age, gender and race from an individual’s face image with high accuracy. Many techniques have been proposed to ensure user privacy, such as visible distortions to the images, manipulation of the original image with new face attributes, face swapping etc. Though these techniques achieve the goal of user privacy by fooling face recognition models, they don’t help the user when they want to upload original images without visible distortions or manipulation. The objective of this work is to implement techniques to ensure the privacy of user’s sensitive or personal data in face images by creating minimum pixel level distortions using white-box and black-box perturbation algorithms to fool AI models while maintaining the integrity of the image, so as to appear the same to a human eye.</p><div><br></div>

show abstract

Unveiling vulnerabilities: evading YOLOv5 object detection through adversarial perturbations and steganography

Sharma,

Garg

2024

Multimed Tools Appl

View full text Add to dashboard Cite

Using FGSM Targeted Attack to Improve the Transferability of Adversarial Example

Cited by 12 publications

References 6 publications

Statistical Detection of Adversarial Examples in Blockchain-Based Federated Forest In-Vehicle Network Intrusion Detection Systems

Statistical Detection of Adversarial Examples in Blockchain-Based Federated Forest In-Vehicle Network Intrusion Detection Systems

Facial Privacy Preservation using FGSM and Universal Perturbation attacks

Unveiling vulnerabilities: evading YOLOv5 object detection through adversarial perturbations and steganography

Contact Info

Product

Resources

About