Towards generalisable and calibrated audio deepfake detection with self-supervised representations
AI4TRUST partners submitted a Paper to discuss how Generalisation—the ability of a model to perform well on unseen data—is crucial for building reliable deepfake detectors. However, recent studies have shown that the current audio deepfake models fall short of this desideratum at Interspeech 2024, Kos, Greece in September 2024.
Early morning hour and evening usage habits increase misinformation-spread
AI4TRUST partners published a paper in Nature Scientific Report on social media manipulation and how it poses a significant threat to cognitive autonomy and unbiased opinion formation in August 2024.
WavLM model ensemble for audio deepfake detection
AI4TRUST partners submitted a Paper at Automatic Speaker Verification and Spoofing Countermeasures Challenge (ASVSpoof5) in August 2024.
Visually Grounded Speech Models Have a Mutual Exclusivity Bias
AI4TRUST partners published a Journal article in Transactions of the Association for Computational Linguistics to investigate the ME bias in the context of visually grounded speech models that learn from natural images and continuous speech audio in June 2024.
Towards Quantitative Evaluation of Explainable AI Methods for Deepfake Detection
AI4TRUST partners submitted a Conference Paper discussing a new framework for evaluating the performance of explanation methods on the decisions of a deepfake detector at Proc. ACM Int. Workshop on Multimedia AI against Disinformation (MAD’24) at the ACM Int. Conf. on Multimedia Retrieval (ICMR’24) in June 2024.
VARIATIONIST: Exploring Multifaceted Variation and Bias in Written Language Data
AI4TRUST partners submitted a paper on Exploring and understanding language data is a fundamental stage in all areas dealing with human language and presented at the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) in Bangkok, Thailand in August 2024
Towards Quantitative Evaluation of Explainable AI Methods for Deepfake Detection
AI4TRUST partners submitted a Conference Paper discussing a new framework for evaluating the performance of explanation methods on the decisions of a deepfake detector at Proc. ACM Int. Workshop on Multimedia AI against Disinformation (MAD’24) at the ACM Int. Conf. on Multimedia Retrieval (ICMR’24) in June 2024.
Novel Class Discovery for Ultra-Fine-Grained Visual Categorization
AI4TRUST partners presented the Novel Class Discovery for Ultra-Fine-Grained Visual Categorization paper at the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) in June 2024.
Federated Generalized Category Discovery
AI4TRUST partners presented the Federated Generalized Category Discovery paper at the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) in June 2024.
PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor
AI4TRUST partners presented PAIR Diffusion paper at the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) in June 2024.
Visually Grounded Few-Shot Word Learning in Low-Resource Settings
AI4TRUST partners published a Journal article in IEEE/ACM Transactions on Audio, Speech, and Language Processing on a visually grounded speech model that learns new words and their visual depictions from just a few word-image example pairs in April 2024.