Conference

Measure and Countermeasure of the Capsulation Attack against Backdoor-based Deep Neural Network Watermarks
Backdoor-based watermarking schemes were proposed to protect the intellectual property of deep neural networks under the black-box …
PDF DOI
Measure and Countermeasure of the Capsulation Attack against Backdoor-based Deep Neural Network Watermarks
FedPrompt: Communication-Efficient and Privacy-Preserving Prompt Tuning in Federated Learning
Federated learning (FL) has enabled global model training on decentralized data in a privacy-preserving way. However, for tasks that …
PDF DOI
FedPrompt: Communication-Efficient and Privacy-Preserving Prompt Tuning in Federated Learning
Content-Insensitive Dynamic Lip Feature Extraction for Visual Speaker Authentication against Deepfake Attacks
Recent research has shown that lip-based speaker authenti- cation system can achieve good authentication performance. However, with …
PDF DOI
Content-Insensitive Dynamic Lip Feature Extraction for Visual Speaker Authentication against Deepfake Attacks
An Auto-Encoder Based Method for Camera Fingerprint Compression
Camera fingerprint links a picture to its camera sensor, which is widely applied in sensor device identification, social network …
PDF DOI
An Auto-Encoder Based Method for Camera Fingerprint Compression
Cross-Domain Local Characteristic Enhanced Deepfake Video Detection
As ultra-realistic face forgery techniques emerge, deepfake detection has attracted increasing attention due to security concerns. Many …
PDF Cite DOI
Cross-Domain Local Characteristic Enhanced Deepfake Video Detection
A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network
Speaker verification has been widely used in many authentication scenarios. However, training models for speaker verification requires …
DOI
Sense-aware BERT and Multi-task Fine-tuning for Multimodal Sentiment Analysis
Humans convey emotions through verbal and non-verbal signals when communicating face-to-face. Pre-trained language model such as BERT …
PDF DOI
Sense-aware BERT and Multi-task Fine-tuning for Multimodal Sentiment Analysis
TIMS: A Novel Approach for Incrementally Few-Shot Text Instance Selection via Model Similarity
Large-scale pre-trained models’ demand for high-quality instances forces people to consider how to select instances for …
PDF Cite DOI
TIMS: A Novel Approach for Incrementally Few-Shot Text Instance Selection via Model Similarity
PPT: Backdoor Attacks on Pre-trained Models via Poisoned Prompt Tuning
Recently, prompt tuning has shown remarkable performance as a new learning paradigm, which freezes pre-trained language models (PLMs) …
PDF DOI
PPT: Backdoor Attacks on Pre-trained Models via Poisoned Prompt Tuning