Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

62124185247 · Jun 202019922001200920172026
48 results for Fake Images

RealStats detects fake images rigorously, combining multiple detectors for robustness.

problem Detecting AI-generated images remains challenging due to evolving generative models.
method Combines training-free statistics to compute p-values and aggregate them for a unified real-image distribution.
result Framework produces interpretable probability scores for robust fake image detection.

Generative Adversarial Networks optimize model parameters for image matching.

problem Optimizing model parameters for accurate image matching.
method Model-Assisted Generative Adversarial Network (GAN) to produce fake images matching true images.
result Best match model parameter values can minimize bias in image recognition.

We introduce a novel approach for training adversarial models by replacing the discriminator score with a bi-modal Gaussian distribution over the real/fake indicator variables. In order to do this, we train the Gaussian classifier to match the target bi-modal distribution implicitly through meta-adversarial training. W…

2017-07-02abs ↗pdf ↗

HDSF detects fake news by learning hierarchical discourse-level structures.

problem Detecting fake news articles with minimal annotated corpora.
method Automatically learns and constructs discourse-level structures for fake and real news articles.
result Real and fake news present substantial differences in hierarchical discourse-level structures.

We study two important concepts in adversarial deep learning---adversarial training and generative adversarial network (GAN). Adversarial training is the technique used to improve the robustness of discriminator by combining adversarial attacker and discriminator in the training phase. GAN is commonly used for image ge…

2018-07-27abs ↗pdf ↗

This study detects fake and automated accounts on Instagram.

problem Fake engagement on Instagram leads to financial loss and wrong audience targeting.
method Two datasets were created and machine learning algorithms like Naive Bayes, Logistic Regression, Support Vector Machines, Neural Networks, and cost-sensitive genetic algorithm were applied.
result 86% accuracy for automated accounts and 96% for fake accounts were achieved.

We propose MAD-GAN, an intuitive generalization to the Generative Adversarial Networks (GANs) and its conditional variants to address the well known problem of mode collapse. First, MAD-GAN is a multi-agent GAN architecture incorporating multiple generators and one discriminator. Second, to enforce that different gener…

2017-04-10abs ↗pdf ↗

MALCOM generates fake comments to fool fake news detectors.

problem Adversaries can manipulate fake news detection models with malicious comments.
method Proposes a novel threat model and develops an adversarial comment generation framework (MALCOM).
result MALCOM can fool fake news detectors 90-94% of the time, depending on the model and dataset.

Improves estimation under model misspecification with fake features.

problem Model misspecification with fake features.
method Proposes a framework to decompose output error into underlying, fake, and missing features.
result Fake features can significantly improve estimation performance, even when not correlated with underlying features.

A fake quadric is a smooth projective surface that has the same rational cohomology as a smooth quadric surface but is not biholomorphic to one. We provide an explicit classification of all irreducible fake quadrics according to the commensurability class of their fundamental group. To accomplish this task, we develop …

2015-04-17abs ↗pdf ↗

We study quotients Γ\HnΓ\backslash \mathbb H^n of the nn-fold product of the upper half plane H\mathbb H by irreducible and torsion-free lattices Γ<PSL2(R)nΓ< PSL_2(\mathbb R)^n with the same Betti numbers as the nn-fold product (P1)n(\mathbb P^1)^n of projective lines. Such varieties are called fake products of projective lines…

2014-11-12abs ↗pdf ↗

In this paper we show strategies to easily identify fake samples generated with the Generative Adversarial Network framework. One strategy is based on the statistical analysis and comparison of raw pixel values and features extracted from them. The other strategy learns formal specifications from the real data and show…

2018-07-13abs ↗pdf ↗

This study improves text summarization and fake news detection using neural models.

problem Improving text summarization and detecting fake news.
method Exploring and comparing different neural models for text summarization, including LSTM-encoder-decoder, pointer-generator networks, and transformers. Applying these models as a feature extractor for fake news detection.
result The proposed neural models enhance text summarization and improve fake news detection accuracy.

Framework detects fake news using weak social signals from multiple sources.

problem Lack of annotated data for early fake news detection.
method Jointly uses weak social signals and clean data to train deep neural networks in a meta-learning framework.
result Framework outperforms state-of-the-art baselines for early fake news detection.

Few-step distillation improves T2I models without real images or CFG trade-offs.

problem Challenges in accelerating T2I models with high-resolution and CFG.
method Score identity distillation (SiD) for few-step generation, with adversarial loss and new guidance strategies.
result State-of-the-art performance on SDXL at 1024x1024 resolution, robust to real images absence.

This work introduces an efficient method to sample high-quality images from conditional GANs.

problem Efficient subsampling of images from conditional GANs (cGANs) is challenging.
method Developed a novel conditional density ratio estimation method (cDRE-F-cSP) and rejection sampling scheme (cDR-RS).
result cDR-RS outperforms state-of-the-art methods in both effectiveness and efficiency.

We give a criterion for a projective surface to become a quotient of a fake projective plane. We also give a detailed information on the elliptic fibration of a (2,3)(2,3)-elliptic surface that is the minimal resolution of a quotient of a fake projective plane. As a consequence, we give a classification of Q{\mathbb Q}-h…

2010-10-02abs ↗pdf ↗

A Triangle Generative Adversarial Network (ΔΔ-GAN) is developed for semi-supervised cross-domain joint distribution matching, where the training data consists of samples from each domain, and supervision of domain correspondence is provided by only a few paired samples. ΔΔ-GAN consists of four neural networks, two ge…

2017-09-19abs ↗pdf ↗

A fake wedge is a diagram of spaces K <- A -> C whose double mapping cylinder is contractible. The terminology stems from the special case A = K v C with maps given by the projections. In this paper, we study the homotopy type of the moduli space D(K,C) of fake wedges on K and C. We formulate two conjectures concerning…

2012-08-10abs ↗pdf ↗