相关论文: Training Data Attribution: Was Your Model Secretly…

LLMs now exhibit human-like skills in various fields, leading to worries about misuse. Thus, detecting generated text is crucial. However, passive detection methods are stuck in domain specificity and limited adversarial robustness. To…

From a simple text prompt, generative-AI image models can create stunningly realistic and creative images bounded, it seems, by only our imagination. These models have achieved this remarkable feat thanks, in part, to the ingestion of…

With the proliferation of AI agents in various domains, protecting the ownership of AI models has become crucial due to the significant investment in their development. Unauthorized use and illegal distribution of these models pose serious…

Deep neural networks have recently achieved significant progress. Sharing trained models of these deep neural networks is very important in the rapid progress of researching or developing deep neural network systems. At the same time, it is…

We investigate the radioactivity of text generated by large language models (LLM), i.e. whether it is possible to detect that such synthetic input was used to train a subsequent LLM. Current methods like membership inference or active IP…

Machine unlearning aims to remove points from the training dataset of a machine learning model after training: e.g., when a user requests their data to be deleted. While many unlearning methods have been proposed, none of them enable users…

Image attribution -- matching an image back to a trusted source -- is an emerging tool in the fight against online misinformation. Deep visual fingerprinting models have recently been explored for this purpose. However, they are not robust…

Duplication is a prevalent issue within datasets. Existing research has demonstrated that the presence of duplicated data in training datasets can significantly influence both model performance and data privacy. However, the impact of data…

Today, creators of data-hungry deep neural networks (DNNs) scour the Internet for training fodder, leaving users with little control over or knowledge of when their data is appropriated for model training. To empower users to counteract…

Current machine learning models achieve super-human performance in many real-world applications. Still, they are susceptible against imperceptible adversarial perturbations. The most effective solution for this problem is adversarial…

Unlearnable examples are proposed to prevent third parties from exploiting unauthorized data, which generates unlearnable examples by adding imperceptible perturbations to public publishing data. These unlearnable examples proficiently…

Latent Diffusion Models (LDMs) enable a wide range of applications but raise ethical concerns regarding illegal utilization. Adding watermarks to generative model outputs is a vital technique employed for copyright tracking and mitigating…

Machine learning models can leak information regarding the dataset they have trained. In this paper, we present the first membership inference attack against black-boxed object detection models that determines whether the given data records…

Transfer learning through the use of pre-trained models has become a growing trend for the machine learning community. Consequently, numerous pre-trained models are released online to facilitate further research. However, it raises…

We present a conceptual framework, datamodeling, for analyzing the behavior of a model class in terms of the training data. For any fixed "target" example $x$, training set $S$, and learning algorithm, a datamodel is a parameterized…

Training data attribution (TDA) techniques find influential training data for the model's prediction on the test data of interest. They approximate the impact of down- or up-weighting a particular training sample. While conceptually useful,…

Many current Internet services rely on inferences from models trained on user data. Commonly, both the training and inference tasks are carried out using cloud resources fed by personal data collected at scale from users. Holding and using…

With the advancement of computer vision and natural language processing, text-to-video generation, enabled by text-to-video diffusion models, has become more prevalent. These models are trained using a large amount of data from the…

The rapid advancement of text-to-image Diffusion Models has led to their widespread public accessibility. However these models, trained on large internet datasets, can sometimes generate undesirable outputs. To mitigate this, approximate…

Unsupervised visual object tracking is a challenging task that requires following arbitrary targets in videos without training on ground-truth annotations. Despite considerable progress, existing state-of-the-art unsupervised trackers often…