From the 1 of 6 linked papers with an AI index.
6 papers
Are DeepFakes Realistic Enough? Exploring Semantic Mismatch as a Novel Challenge
Sharayu Nilesh Deshmukh, Kailash A. Hambarde, Joana C. Costa +2
The paper introduces a new evaluation class for DeepFake detection that captures semantic inconsistencies between audio and video (RARV‑SMM) and tests how current models handle suc…
ZQBA: Zero Query Black-box Adversarial Attack
Joana C. Costa, Tiago Roxo, Hugo Proença +1
Current black-box adversarial attacks either require multiple queries or diffusion models to produce adversarial samples that can impair the target model performance. However, thes…
LISArD: Learning Image Similarity to Defend Against Gray-box Adversarial Attacks
Joana C. Costa, Tiago Roxo, Hugo Proença +1
State-of-the-art defense mechanisms are typically evaluated in the context of white-box attacks, which is not realistic, as it assumes the attacker can access the gradients of the…
ASDnB: Merging Face with Body Cues For Robust Active Speaker Detection
Tiago Roxo, Joana C. Costa, Pedro Inácio +1
State-of-the-art Active Speaker Detection (ASD) approaches mainly use audio and facial features as input. However, the main hypothesis in this paper is that body dynamics is also h…
BIAS: A Body-based Interpretable Active Speaker Approach
Tiago Roxo, Joana C. Costa, Pedro R. M. Inácio +1
State-of-the-art Active Speaker Detection (ASD) approaches heavily rely on audio and facial features to perform, which is not a sustainable approach in wild scenarios. Although the…
How to Squeeze An Explanation Out of Your Model
Tiago Roxo, Joana C. Costa, Pedro R. M. Inácio +1
Deep learning models are widely used nowadays for their reliability in performing various tasks. However, they do not typically provide the reasoning behind their decision, which i…