2 citations · 8 across the 13 of their papers we have counts for
13 papers
Representation and Reference Selection in Training-Free Synthetic Image Attribution
Meiling Li, Pietro Bongini, Benedetta Tondi +1
Synthetic image attribution aims at identifying the generator responsible for a given AI-generated image. Training-free reference-based attribution methods are easily scalable, sin…
The Role of Input Dimensionality in the Emergence and Targeted Control of Adversarial Examples
Nasrin Malekzadeh Goradel, Niccolo Pancino, Yaser Gholizade Atani +3
Several theoretical works have tried to explain the adversarial vulnerability of deep neural networks through properties of high-dimensional geometry. However, the assumptions unde…
Enhancing Visual Sentiment Analysis via Semiotic Isotopy-Guided Dataset Construction
Marco Blanchini, Giovanna Maria Dimitri, Benedetta Tondi +2
Visual Sentiment Analysis (VSA) is a challenging task due to the vast diversity of emotionally salient images and the inherent difficulty of acquiring sufficient data to capture th…
Training-free Source Attribution of AI-generated Images via Resynthesis
Pietro Bongini, Valentina Molinari, Andrea Costanzo +2
Synthetic image source attribution is a challenging task, especially in data scarcity conditions requiring few-shot or zero-shot classification capabilities. We present a new train…
Of-SemWat: High-payload text embedding for semantic watermarking of AI-generated images with arbitrary size
Benedetta Tondi, Andrea Costanzo, Mauro Barni
We propose a high-payload image watermarking method for textual embedding, where a semantic description of the image - which may also correspond to the input text prompt-, is embed…
WILD: a new in-the-Wild Image Linkage Dataset for synthetic image attribution
Pietro Bongini, Sara Mandelli, Andrea Montibeller +14
Synthetic image source attribution is an open challenge, with an increasing number of image generators being released yearly. The complexity and the sheer number of available gener…
An Efficient Watermarking Method for Latent Diffusion Models via Low-Rank Adaptation and Dynamic Loss Weighting
Dongdong Lin, Yue Li, Benedetta Tondi +3
The rapid proliferation of Deep Neural Networks (DNNs) is driving a surge in model watermarking technologies, as the trained models themselves constitute valuable intellectual prop…
Deepfake Media Forensics: State of the Art and Challenges Ahead
Irene Amerini, Mauro Barni, Sebastiano Battiato +21
AI-generated synthetic media, also called Deepfakes, have significantly influenced so many domains, from entertainment to cybersecurity. Generative Adversarial Networks (GANs) and…
BOSC: A Backdoor-based Framework for Open Set Synthetic Image Attribution
Jun Wang, Benedetta Tondi, Mauro Barni
Synthetic image attribution addresses the problem of tracing back the origin of images produced by generative models. Extensive efforts have been made to explore unique representat…
JMA: a General Algorithm to Craft Nearly Optimal Targeted Adversarial Example
Benedetta Tondi, Wei Guo, Niccolò Pancino +1
Most of the approaches proposed so far to craft targeted adversarial examples against Deep Learning classifiers are highly suboptimal and typically rely on increasing the likelihoo…
Robust Retraining-free GAN Fingerprinting via Personalized Normalization
Jianwei Fei, Zhihua Xia, Benedetta Tondi +1
In recent years, there has been significant growth in the commercial applications of generative models, licensed and distributed by model developers to users, who in turn use them…
Wide Flat Minimum Watermarking for Robust Ownership Verification of GANs
Jianwei Fei, Zhihua Xia, Benedetta Tondi +1
We propose a novel multi-bit box-free watermarking method for the protection of Intellectual Property Rights (IPR) of GANs with improved robustness against white-box attacks like f…
A Siamese-based Verification System for Open-set Architecture Attribution of Synthetic Images
Lydia Abady, Jun Wang, Benedetta Tondi +1
Despite the wide variety of methods developed for synthetic image attribution, most of them can only attribute images generated by models or architectures included in the training…