相关论文: Reconstructing training data from document underst…

LLMs trained on massive datasets may inadvertently acquire sensitive information such as personal details and potentially harmful content. This risk is further heightened in multimodal LLMs as they integrate information from multiple…

While Code Language Models (CLMs) have demonstrated superior performance in software engineering tasks such as code generation and summarization, recent empirical studies reveal a critical privacy vulnerability: these models exhibit…

The widespread adoption of large language models (LLMs) has raised concerns regarding data privacy. This study aims to investigate the potential for privacy invasion through input reconstruction attacks, in which a malicious model provider…

Diffusion models are renowned for their state-of-the-art performance in generating synthetic images. However, concerns related to safety, privacy, and copyright highlight the need for machine unlearning, which can make diffusion models…

Data reconstruction attacks on trained neural networks aim to recover the data on which the network has been trained and pose a significant threat to privacy, especially if the training dataset contains sensitive information. Here, we…

Federated learning is a decentralized machine learning approach where clients train models locally and share model updates to develop a global model. This enables low-resource devices to collaboratively build a high-quality model without…

Deep neural network-based image compression has been extensively studied. However, the model robustness which is crucial to practical application is largely overlooked. We propose to examine the robustness of prevailing learned image…

As Large Language Models (LLMs) demonstrate extensive capability in learning from documents, LLM unlearning becomes an increasingly important research area to address concerns of LLMs in terms of privacy, copyright, etc. A conventional LLM…

Large language models (LLMs) are widely adapted for downstream applications through fine-tuning, a process named customization. However, recent studies have identified a vulnerability during this process, where malicious samples can…

The increasing reliance on diffusion models for generating synthetic images has amplified concerns about the unauthorized use of personal data, particularly facial images, in model training. In this paper, we introduce a novel identity…

The reconstruction of shredded documents consists in arranging the pieces of paper (shreds) in order to reassemble the original aspect of such documents. This task is particularly relevant for supporting forensic investigation as documents…

Language models (LMs) risk inadvertently memorizing and divulging sensitive or personally identifiable information (PII) seen in training data, causing privacy concerns. Current approaches to address this issue involve costly dataset…

The challenge of WAD (web attack detection) is growing as hackers continuously refine their methods to evade traditional detection. Deep learning models excel in handling complex unknown attacks due to their strong generalization and…

Current research in adversarial robustness of LLMs focuses on discrete input manipulations in the natural language space, which can be directly transferred to closed-source models. However, this approach neglects the steady progression of…

Optical Character Recognition (OCR) for data extraction from documents is essential to intelligent informatics, such as digitizing medical records and recognizing road signs. Multi-modal Large Language Models (LLMs) can solve this task and…

Deep learning models have been used widely for various purposes in recent years in object recognition, self-driving cars, face recognition, speech recognition, sentiment analysis, and many others. However, in recent years it has been shown…

Membership inference (MI) determines if a sample was part of a victim model training set. Recent development of MI attacks focus on record-level membership inference which limits their application in many real-world scenarios. For example,…

Machine learning models are vulnerable to membership inference attack, which can be used to determine whether a given sample appears in the training data. Most existing methods assume the attacker has full access to the features of the…

With the ongoing popularization of online services, the digital document images have been used in various applications. Meanwhile, there have emerged some deep learning-based text editing algorithms which alter the textual information of an…

Generative models can unintentionally memorize training data, posing significant privacy risks. This paper addresses the memorization phenomenon in time series imputation models, introducing the Loss-Based with Reference Model (LBRM)…