5 papers
Human-AI Ensembles Improve Deepfake Detection in Low-to-Medium Quality Videos
Marco Postiglione, Isabel Gortner, V. S. Subrahmanian
Deepfake detection is widely framed as a machine learning problem, yet how humans and AI detectors compare under realistic conditions remains poorly understood. We evaluate 200 hum…
SMART: A Social Movement Analysis & Reasoning Tool with Case Studies on #MeToo and #BlackLivesMatter
Valerio La Gatta, Marco Postiglione, Jeremy Gilbert +4
Social movements supporting the UN's Sustainable Development Goals (SDGs) play a vital role in improving human lives. If journalists were aware of the relationship between social m…
Context and Transcripts Improve Detection of Deepfake Audios of Public Figures
Chongyang Gao, Marco Postiglione, Julian Baldwin +6
Humans use context to assess the veracity of information. However, current audio deepfake detectors only analyze the audio file without considering either context or transcripts. W…
DEEP: A Discourse Evolution Engine for Predictions about Social Movements
Valerio La Gatta, Marco Postiglione, Jeremy Gilbert +4
Numerous social movements (SMs) around the world help support the UN's Sustainable Development Goals (SDGs). Understanding how key events shape SMs is key to the achievement of the…
Perturbed Public Voices (PV): A Dataset for Robust Audio Deepfake Detection
Chongyang Gao, Marco Postiglione, Isabel Gortner +2
Current audio deepfake detectors cannot be trusted. While they excel on controlled benchmarks, they fail when tested in the real world. We introduce Perturbed Public Voices (P$^{2}…