Search Results for author:
Found 15 papers, 6 papers with code
ManiFPT: Defining and Analyzing Fingerprints of Generative Models
Recent works have shown that generative models leave traces of their underlying generative process on the generated samples, broadly referred to as fingerprints of a generative model, and have studied their utility in detecting synthetic images from real ones.
Unsupervised Multimodal Deepfake Detection Using Intra- and Cross-Modal Inconsistencies
Deepfake videos present an increasing threat to society with potentially negative impact on criminal justice, democracy, and personal safety and privacy.
SABAF: Removing Strong Attribute Bias from Neural Networks with Adversarial Filtering
To that end, in this work, we mathematically and empirically reveal the limitation of existing attribute bias removal methods in presence of strong bias and propose a new method that can mitigate this limitation.
Information-Theoretic Bounds on The Removal of Attribute-Specific Bias From Neural Networks
Ensuring a neural network is not relying on protected attributes (e. g., race, sex, age) for predictions is crucial in advancing fair and trustworthy AI.
Shadow Datasets, New challenging datasets for Causal Representation Learning
Most causal representation learning (CRL) methods are fully supervised, which is impractical due to costly labeling.
Emergent Asymmetry of Precision and Recall for Measuring Fidelity and Diversity of Generative Models in High Dimensions
Precision and Recall are two prominent metrics of generative performance, which were proposed to separately measure the fidelity and diversity of generative models.
Trojan Model Detection Using Activation Optimization
TRIGS delivers the best performance on the new dataset, surpassing the baseline methods by a large margin.
A Critical View of Vision-Based Long-Term Dynamics Prediction Under Environment Misalignment
In this paper, we investigate two challenging conditions for environment misalignment: Cross-Domain and Cross-Context by proposing four datasets that are designed for these challenges: SimB-Border, SimB-Split, BlenB-Border, and BlenB-Split.
MONet: Multi-scale Overlap Network for Duplication Detection in Biomedical Images
Manipulation of biomedical images to misrepresent experimental results has plagued the biomedical community for a while.
Learning Robust Representations Of Generative Models Using Set-Based Artificial Fingerprints
We then improve the stability and attributability of the fingerprints by proposing a new learning method based on set-encoding and contrastive training.
Do-Operation Guided Causal Representation Learning with Reduced Supervision Strength
Causal representation learning has been proposed to encode relationships between factors presented in the high dimensional data.
Attack-Agnostic Adversarial Detection
The growing number of adversarial attacks in recent years gives attackers an advantage over defenders, as defenders must train detectors after knowing the types of attacks, and many models need to be maintained to ensure good performance in detecting any upcoming attacks.
Introducing the DOME Activation Functions
The function can also be extended to the case of multi-class classification, and used as an alternative to the standard softmax function.
BioFors: A Large Biomedical Image Forensics Dataset
Our results and analysis show that existing algorithms developed on common computer vision datasets are not robust when applied to biomedical images, validating that more research is required to address the unique challenges of biomedical image forensics.
MEG: Multi-Evidence GNN for Multimodal Semantic Forensics
The problem setup requires algorithms to perform multimodal semantic forensics to authenticate a query multimedia package using a reference dataset of potentially related packages as evidences.
