相关论文: Box-Free Model Watermarks Are Prone to Black-Box R…

Language models (LMs) have emerged as critical intellectual property (IP) assets that necessitate protection. Although various watermarking strategies have been proposed, they remain vulnerable to Linear Functionality Equivalence Attack…

In recent years, LLM watermarking has emerged as an attractive safeguard against AI-generated content, with promising applications in many real-world domains. However, there are growing concerns that the current LLM watermarking schemes are…

Deep learning techniques have implemented many unconditional image generation (UIG) models, such as GAN, Diffusion model, etc. The extremely realistic images (also known as AI-Generated Content, AIGC for short) produced by these models…

Backdoor attack aims to deceive a victim model when facing backdoor instances while maintaining its performance on benign data. Current methods use manual patterns or special perturbations as triggers, while they often overlook the…

Artificial Intelligence Generated Content (AIGC), particularly video generation with diffusion models, has been advanced rapidly. Invisible watermarking is a key technology for protecting AI-generated videos and tracing harmful content, and…

This paper introduces EmMark,a novel watermarking framework for protecting the intellectual property (IP) of embedded large language models deployed on resource-constrained edge devices. To address the IP theft risks posed by malicious…

Watermarking is a key technique for detecting AI-generated text. In this work, we study its vulnerabilities and introduce the Smoothing Attack, a novel watermark removal method. By leveraging the relationship between the model's confidence…

Training machine learning (ML) models is expensive in terms of computational power, amounts of labeled data and human expertise. Thus, ML models constitute intellectual property (IP) and business value for their owners. Embedding digital…

Deep neural networks provide unprecedented performance in all image classification problems, taking advantage of huge amounts of data available for training. Recent studies, however, have shown their vulnerability to adversarial attacks,…

EEG-based neural networks, pivotal in medical diagnosis and brain-computer interfaces, face significant intellectual property (IP) risks due to their reliance on sensitive neurophysiological data and resource-intensive development. Current…

Methods for watermarking large language models have been proposed that distinguish AI-generated text from human-generated text by slightly altering the model output distribution, but they also distort the quality of the text, exposing the…

Watermarking has been widely adopted for protecting the intellectual property (IP) of Deep Neural Networks (DNN) to defend the unauthorized distribution. Unfortunately, the popular data-poisoning DNN watermarking scheme relies on target…

In recent years, tremendous success has been witnessed in Retrieval-Augmented Generation (RAG), widely used to enhance Large Language Models (LLMs) in domain-specific, knowledge-intensive, and privacy-sensitive tasks. However, attackers may…

Adoption of machine learning models across industries have turned Neural Networks (DNNs) into a prized Intellectual Property (IP), which needs to be protected from being stolen or being used without authorization. This topic gave rise to…

Recently, Deep Learning (DL) models have been increasingly deployed on end-user devices as On-Device AI, offering improved efficiency and privacy. However, this deployment trend poses more serious Intellectual Property (IP) risks, as models…

The state of the art performance of deep learning models comes at a high cost for companies and institutions, due to the tedious data collection and the heavy processing requirements. Recently, [35, 22] proposed to watermark convolutional…

Well-performed deep neural networks (DNNs) generally require massive labelled data and computational resources for training. Various watermarking techniques are proposed to protect such intellectual properties (IPs), wherein the DNN…

Generative AI technology has become increasingly integrated into our daily lives, offering powerful capabilities to enhance productivity. However, these same capabilities can be exploited by adversaries for malicious purposes. While…

As frontier AIs become more powerful and costly to develop, adversaries have increasing incentives to steal model weights by mounting exfiltration attacks. In this work, we consider exfiltration attacks where an adversary attempts to sneak…

In fragile watermarking, a sensitive watermark is embedded in an object in a manner such that the watermark breaks upon tampering. This fragile process can be used to ensure the integrity and source of watermarked objects. While fragile…