DeT: Defending Against Adversarial Examples via Decreasing Transferability

Li, Changjiang; Weng, Haiqin; Ji, Shouling; Dong, Jianfeng; He, Qinming

doi:10.1007/978-3-030-37337-5_25

Cited by 7 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most adversarial examples are inherently unstable. Previous studies [23], [65], [28] have shown that adversarial examples experience a trade-off between transferability and imperceptibility, i.e., the imperceptible adversarial examples generated from the surrogate model can hardly fool the target model. To show that adversarial texts also have low transferability, we first train two models from the same training dataset, generate adversarial texts from one model, and then transfer them to another.…”

Section: A Design Intuitionmentioning

confidence: 99%

Improving the Robustness of Transformer-based Large Language Models with Dynamic Attention

Shen,

Pu,

et al. 2024

Proceedings 2024 Network and Distributed System Security Symposium

Self Cite

View full text Add to dashboard Cite

Section: A Design Intuitionmentioning

confidence: 99%

Improving the Robustness of Transformer-based Large Language Models with Dynamic Attention

Shen,

Pu,

et al. 2024

Proceedings 2024 Network and Distributed System Security Symposium

Self Cite

View full text Add to dashboard Cite

“…Jiachen et al [28] proposed a novel black-box adversarial sensor attack targeting the security of autonomous driving perception models. To defend against adversarial examples, Changjiang et al [29] designed a transferability-based approach for both black and gray box attacks on deep neural networks.…”

Section: Attack and Defense In Other Layersmentioning

confidence: 99%

FakeSwarm: Improving Fake News Detection with Swarming Characteristics

Wu¹,

Ye²

2023

Natural Language Processing and Machine Learning

View full text Add to dashboard Cite

The proliferation of fake news poses a serious threat to society, as it can misinform and manipulate the public, erode trust in institutions, and undermine democratic processes. To address this issue, we present FakeSwarm, a fake news identification system that leverages the swarming characteristics of fake news. We propose a novel concept of fake news swarming characteristics and design three types of swarm features, including principal component analysis, metric representation, and position encoding, to extract the swarm behavior. We evaluate our system on a public dataset and demonstrate the effectiveness of incorporating swarm features in fake news identification, achieving an f1-score and accuracy over 97% by combining all three types of swarm features. Furthermore, we design an online learning pipeline based on the hypothesis of the temporal distribution pattern of fake news emergence, which is validated on a topic with early emerging fake news and a shortage of text samples, showing that swarm features can significantly improve recall rates in such cases. Our work provides a new perspective and approach to fake news detection and highlights the importance of considering swarming characteristics in detecting fake news.

show abstract

A state-of-the-art review on adversarial machine learning in image classification

Bajaj

Vishwakarma

2023

Multimed Tools Appl

View full text Add to dashboard Cite

DeT: Defending Against Adversarial Examples via Decreasing Transferability

Cited by 7 publications

References 16 publications

Improving the Robustness of Transformer-based Large Language Models with Dynamic Attention

Improving the Robustness of Transformer-based Large Language Models with Dynamic Attention

FakeSwarm: Improving Fake News Detection with Swarming Characteristics

A state-of-the-art review on adversarial machine learning in image classification

Contact Info

Product

Resources

About