2021
DOI: 10.48550/arxiv.2112.13416
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Attribute Inference Attack of Speech Emotion Recognition in Federated Learning Settings

Abstract: Speech emotion recognition (SER) processes speech signals to detect and characterize expressed perceived emotions. Many SER application systems often acquire and transmit speech data collected at the client-side to remote cloud platforms for inference and decision making. However, speech data carry rich information not only about emotions conveyed in vocal expressions, but also other sensitive demographic traits such as gender, age and language background. Consequently, it is desirable for SER systems to have … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
15
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
4

Relationship

2
2

Authors

Journals

citations
Cited by 4 publications
(15 citation statements)
references
References 29 publications
0
15
0
Order By: Relevance
“…For instance, many works have demonstrated that data reconstruction is achievable through analyzing the model updates in FL setup [8,9,10]. We had previously demonstrated this phenomenon in FL-based SER setup [6]. Specifically, we showed that an attribute inference attacker could successfully infer a user's gender attribute by using the model updates shared in the FL setup [6].…”
Section: Introductionmentioning
confidence: 78%
See 3 more Smart Citations
“…For instance, many works have demonstrated that data reconstruction is achievable through analyzing the model updates in FL setup [8,9,10]. We had previously demonstrated this phenomenon in FL-based SER setup [6]. Specifically, we showed that an attribute inference attacker could successfully infer a user's gender attribute by using the model updates shared in the FL setup [6].…”
Section: Introductionmentioning
confidence: 78%
“…In this section, we first review the attacking framework we proposed in [6]. We then summarise the proposed UDP algorithm used in this work.…”
Section: Methodsmentioning
confidence: 99%
See 2 more Smart Citations
“…return θ, c ′ , ∇c prior work [25]. Finally, we calculate the global average of the last layer's hidden state as the final feature from the pre-trained model's output.…”
mentioning
confidence: 99%