Modern communication does not rely anymore solely on mainstream media like newspapers or television, but rather takes place over social networks, in real-time, and with live interactions among users. The speedup of distribution and the amount of information available, however, also led to an increased amount of misleading content, disinformation and propaganda. Conversely, the fight against disinformation, in which news agencies and NGOs (among others) take part on a daily basis to avoid the risk of citizens’ opinions being distorted, became even more crucial and demanding, especially for what concerns sensitive topics such as politics, health and religion.
Disinformation campaigns are leveraging, among others, AI-based tools for content generation and modification: hyper-realistic visual, speech, textual and video content have emerged under the collective name of “deepfakes”, and more recently with the use of Large Language Models (LLMs) and Large Multimodal Models (LMMs), undermining the perceived credibility of media content. It is, therefore, even more crucial to counter these advances by devising new robust and trustworthy AI tools able to detect the presence of inaccurate, synthetic and manipulated content, accessible to journalists and fact-checkers.
Future multimedia disinformation detection research relies on the combination of different modalities and on the adoption of the latest advances of deep learning approaches and architectures. These raise new challenges and questions that need to be addressed to reduce the effects of disinformation campaigns. The workshop, in its fourth edition, welcomes contributions related to different aspects of AI-powered disinformation detection, analysis and mitigation.
Topics of interest include but are not limited to:
- Disinformation detection in multimedia content (e.g., video, audio, texts, images)
- Multimodal verification methods
- Synthetic and manipulated media detection
- Multimedia forensics
- Disinformation spread and effects in social media
- Analysis of disinformation campaigns in societally-sensitive domains
- Robustness of media verification against adversarial attacks and real-world complexities
- Fairness and non-discrimination of disinformation detection in multimedia content
- Explaining disinformation detection results to non-expert users
- Temporal and cultural aspects of disinformation
- Dataset sharing and governance in AI for disinformation
- Datasets for disinformation detection and multimedia verification
- Open resources, e.g., datasets, software tools
- Large Language Models for analyzing and mitigating disinformation campaigns
- Large Multimodal Models for media verification
- Multimedia verification systems and applications
- System fusion, ensembling and late fusion techniques
- Benchmarking and evaluation framework
Fraunhofer Institute for Digital Media Technology IDMT