相关论文: Statistical Watermarking for Networked Control Sys…

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…

Integrating watermarking into the generation process of latent diffusion models (LDMs) simplifies detection and attribution of generated content. Semantic watermarks, such as Tree-Rings and Gaussian Shading, represent a novel class of…

Autonomous vehicles, including self driving cars, ground robots, and drones, rely on multi-modal sensor pipelines for safe operation, yet remain vulnerable to adversarial sensor attacks. A critical gap is the lack of a systematic end-to-end…

Watermarking enables GenAI providers to verify whether content was generated by their models. A watermark is a hidden signal in the content, whose presence can be detected using a secret watermark key. A core security threat are forgery…

In this paper, we propose a fault detection and isolation based attack-aware multi-sensor integration algorithm for the detection of cyberattacks in autonomous vehicle navigation systems. The proposed algorithm uses an extended Kalman…

In this work, we focus on analyzing vulnerability of nonlinear dynamical control systems to stealthy sensor attacks. We start by defining the notion of stealthy attacks in the most general form by leveraging Neyman-Pearson lemma;…

Sensor systems are extremely popular today and vulnerable to sensor data attacks. Due to possible devastating consequences, counteracting sensor data attacks is an extremely important topic, which has not seen sufficient study. This paper…

Contrastive learning (CL) reduces annotation cost via auto-derived supervisory signals. Since large-scale in-house CL datasets are infeasible, reliance on third-party or internet data is common. Recent studies show CL models are vulnerable…

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…

We examine the merit of Bernoulli packet drops in actively detecting integrity attacks on control systems. The aim is to detect an adversary who delivers fake sensor measurements to a system operator in order to conceal their effect on the…

Whereas the embedding distortion, the payload and the robustness of digital watermarking schemes are well understood, the notion of security is still not completely well defined. The approach proposed in the last five years is too…

In this paper, we investigate data-driven attack detection and identification in a model-free setting. We consider a practically motivated scenario in which the available dataset may be compromised by malicious sensor attacks, but contains…

Potential harms of large language models can be mitigated by watermarking model output, i.e., embedding signals into generated text that are invisible to humans but algorithmically detectable from a short span of tokens. We propose a…

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…

Watermark has been widely deployed by industry to detect AI-generated images. The robustness of such watermark-based detector against evasion attacks in the white-box and black-box settings is well understood in the literature. However, the…

Attacks, including the manipulation of sensor readings and the modification of actuator commands, pose a significant challenge to the security and privacy of automated systems. This paper considers discrete event systems that can be modeled…

The most effective techniques to detect LLM-generated text rely on inserting a detectable signature -- or watermark -- during the model's decoding process. Most existing watermarking methods require access to the underlying LLM's logits,…

Recent advancements in Large Language Models (LLMs) raised concerns over potential misuse, such as for spreading misinformation. In response two counter measures emerged: machine learning-based detectors that predict if text is synthetic,…

Amidst rising concerns about the internet being proliferated with content generated from language models (LMs), watermarking is seen as a principled way to certify whether text was generated from a model. Many recent watermarking techniques…

This work presents a rigorous analysis of the adverse effects of cyber-physical attacks on discrete-time distributed multi-agent systems, and propose a mitigation approach for attacks on sensors and actuators. First, we show how an attack…