相关论文: Provable Watermarking for Data Poisoning Attacks

Protecting the Intellectual Property rights of DNN models is of primary importance prior to their deployment. So far, the proposed methods either necessitate changes to internal model parameters or the machine learning pipeline, or they…

Neural networks are successfully used in a variety of applications, many of them having safety and security concerns. As a result researchers have proposed formal verification techniques for verifying neural network properties. While…

The widespread use of Large Language Models (LLMs) in text generation has raised increasing concerns about intellectual property disputes. Watermarking techniques, which embed meta information into AI-generated content (AIGC), have the…

Data poisoning and leakage risks impede the massive deployment of federated learning in the real world. This chapter reveals the truths and pitfalls of understanding two dominating threats: {\em training data privacy intrusion} and {\em…

Text watermarking for Large Language Models (LLMs) has made significant progress in detecting LLM outputs and preventing misuse. Current watermarking techniques offer high detectability, minimal impact on text quality, and robustness to…

Ownership verification for neural networks is important for protecting these models from illegal copying, free-riding, re-distribution and other intellectual property misuse. We present a novel methodology for neural network ownership…

The development of large language models (LLMs) has raised concerns about potential misuse. One practical solution is to embed a watermark in the text, allowing ownership verification through watermark extraction. Existing methods primarily…

Gradient attacks and data poisoning tamper with the training of machine learning algorithms to maliciously alter them and have been proven to be equivalent in convex settings. The extent of harm these attacks can produce in non-convex…

The rapid advancement of text-to-image generation systems, exemplified by models like Stable Diffusion, Midjourney, Imagen, and DALL-E, has heightened concerns about their potential misuse. In response, companies like Meta and Google have…

The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data. In this work, we show that adversarial examples, originally intended for attacking pre-trained…

AI-generated content has accelerated the topic of media synthesis, particularly Deepfake, which can manipulate our portraits for positive or malicious purposes. Before releasing these threatening face images, one promising forensics…

Deep learning models are often trained on distributed, web-scale datasets crawled from the internet. In this paper, we introduce two new dataset poisoning attacks that intentionally introduce malicious examples to a model's performance. Our…

The recent explosion of high-quality language models has necessitated new methods for identifying AI-generated text. Watermarking is a leading solution and could prove to be an essential tool in the age of generative AI. Existing approaches…

Watermarking is a tool for actively identifying and attributing the images generated by latent diffusion models. Existing methods face the dilemma of image quality and watermark robustness. Watermarks with superior image quality usually…

The rapid advancement of large language models (LLMs) has raised concerns regarding their potential misuse, particularly in generating fake news and misinformation. To address these risks, watermarking techniques for autoregressive language…

A variety of anomaly detection schemes have been proposed to detect malicious attacks to Cyber-Physical Systems. Among these schemes, Dynamic Watermarking methods have been proven highly effective at detecting a wide range of attacks.…

A number of online services nowadays rely upon machine learning to extract valuable information from data collected in the wild. This exposes learning algorithms to the threat of data poisoning, i.e., a coordinate attack in which a fraction…

The network flow watermarking technique associates the two communicating parties by actively modifying certain characteristics of the stream generated by the sender so that it covertly carries some special marking information. Some curious…

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…

Model watermarking techniques can embed watermark information into the protected model for ownership declaration by constructing specific input-output pairs. However, existing watermarks are easily removed when facing model stealing…