Publications by authors named "Matthew Groh"
Article Synopsis
- Recent advancements in technology have made it increasingly difficult for people to distinguish between real political speeches and deepfake videos due to hyper-realistic audio and visual effects.
- A study involving 2,215 participants found that factors like misinformation rates and question framing did not significantly impact people’s ability to identify authenticity.
- The research revealed that deepfake videos with advanced text-to-speech audio were harder to detect than those with voice actors, and overall, people relied more on audio and visual cues rather than the content of the speech to discern real from fake.
Article Synopsis
- Advances in deep learning systems show promise for improving clinical decision-making in medical diagnoses, but the effectiveness of combining physician expertise with machine learning is still uncertain, particularly when dealing with underrepresented populations.
- A large-scale study involving nearly 850 physicians evaluated their diagnostic accuracy using a teledermatology simulation with 364 skin disease images, revealing that specialist dermatologists had an accuracy of 38% while primary-care physicians had only 19%.
- Although the integration of fair deep learning assistance improved overall diagnostic accuracy by over 33%, it highlighted and worsened the existing diagnostic disparities between skin tones, showing that enhancing accuracy doesn't eliminate bias in the system.
Understanding shifts in creative work will help guide AI's impact on the media ecosystem.
View Article and Find Full Text PDFDeepfake detection by human crowds, machines, and machine-informed crowds.
Proc Natl Acad Sci U S A
January 2022
The recent emergence of machine-manipulated media raises an important societal question: How can we know whether a video that we watch is real or fake? In two online studies with 15,016 participants, we present authentic videos and deepfakes and ask participants to identify which is which. We compare the performance of ordinary human observers with the leading computer vision deepfake detection model and find them similarly accurate, while making different kinds of mistakes. Together, participants with access to the model's prediction are more accurate than either alone, but inaccurate model predictions often decrease participants' accuracy.
View Article and Find Full Text PDFToward understanding the impact of artificial intelligence on labor.
Proc Natl Acad Sci U S A
April 2019
Rapid advances in artificial intelligence (AI) and automation technologies have the potential to significantly disrupt labor markets. While AI and automation can augment the productivity of some workers, they can replace the work done by others and will likely transform almost all occupations at least to some degree. Rising automation is happening in a period of growing economic inequality, raising fears of mass technological unemployment and a renewed call for policy efforts to address the consequences of technological change.
View Article and Find Full Text PDF