相关论文: DROPWAT: an Invisible Network Flow Watermark for D…

Recent advances in the capabilities of large language models such as GPT-4 have spurred increasing concern about our ability to detect AI-generated text. Prior works have suggested methods of embedding watermarks in model outputs, by…

Learning topological representation of a network in dynamic environments has recently attracted considerable attention due to the time-evolving nature of many real-world networks i.e. nodes/links might be added/removed as time goes on.…

LLM watermarking has attracted attention as a promising way to detect AI-generated content, with some works suggesting that current schemes may already be fit for deployment. In this work we dispute this claim, identifying watermark…

Due to the rapid growth of machine learning tools and specifically deep networks in various computer vision and image processing areas, application of Convolutional Neural Networks for watermarking have recently emerged. In this paper, we…

Traffic anomalies and attacks are commonplace in today's networks and identifying them rapidly and accurately is critical for large network operators. For a statistical intrusion detection system (IDS), it is crucial to detect at the…

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…

Benchmark datasets for network intrusion detection commonly rely on synthetically generated traffic, which fails to reflect the statistical variability and temporal drift encountered in operational environments. This paper introduces…

Flow correlation is the core technique used in a multitude of deanonymization attacks on Tor. Despite the importance of flow correlation attacks on Tor, existing flow correlation techniques are considered to be ineffective and unreliable in…

With the significant advances in deep generative models for image and video synthesis, Deepfakes and manipulated media have raised severe societal concerns. Conventional machine learning classifiers for deepfake detection often fail to cope…

Constructing and curating high-quality code datasets requires significant resources, making them valuable intellectual property. Unfortunately, these datasets currently face severe risks of unauthorized use. Although digital watermarking…

The malicious applications of deep forgery, represented by face swapping, have introduced security threats such as misinformation dissemination and identity fraud. While some research has proposed the use of robust watermarking methods to…

Obtaining the state of the art performance of deep learning models imposes a high cost to model generators, due to the tedious data preparation and the substantial processing requirements. To protect the model from unauthorized…

Current probabilistic flow-size monitoring can only detect heavy hitters (e.g., flows utilizing 10 times their permitted bandwidth), but cannot detect smaller overuse (e.g., flows utilizing 50-100% more than their permitted bandwidth).…

Cyberthreats are a permanent concern in our modern technological world. In the recent years, sophisticated traffic analysis techniques and anomaly detection (AD) algorithms have been employed to face the more and more subversive adversarial…

Watermarking is a technique to help identify the source of data points, which can be used to help prevent the misuse of protected datasets. Existing methods on code watermarking, leveraging the idea from the backdoor research, embed…

Software vulnerabilities represent one of the most pressing threats to computing systems. Identifying vulnerabilities in source code is crucial for protecting user privacy and reducing economic losses. Traditional static analysis tools rely…

Data has been regarded as a valuable asset with the fast development of artificial intelligence technologies. In this paper, we introduce deep-learning neural network-based frequency-domain watermarking for protecting energy system time…

Deepfakes generated by modern generative models pose a serious threat to information integrity, digital identity, and public trust. Existing detection methods are largely reactive, attempting to identify manipulations after they occur and…

Dataset Condensation (DC) is a data-efficient learning paradigm that synthesizes small yet informative datasets, enabling models to match the performance of full-data training. However, recent work exposes a critical vulnerability of DC to…

Recently, how to protect the Intellectual Property (IP) of deep neural networks (DNN) becomes a major concern for the AI industry. To combat potential model piracy, recent works explore various watermarking strategies to embed secret…