Related papers: Improved Pseudorandom Codes from Permuted Puzzles

Recent advances in LLM watermarking methods such as SynthID-Text by Google DeepMind offer promising solutions for tracing the provenance of AI-generated text. However, our robustness assessment reveals that SynthID-Text is vulnerable to…

Despite numerous countermeasures proposed by practitioners and researchers, remote control-flow alteration of programs with memory-safety vulnerabilities continues to be a realistic threat. Guaranteeing that complex software is completely…

The rapid adoption of large language models (LLMs), such as GPT-4 and Claude 3.5, underscores the need to distinguish LLM-generated text from human-written content to mitigate the spread of misinformation and misuse in education. One…

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…

Deepfake facial manipulation has garnered significant public attention due to its impacts on enhancing human experiences and posing privacy threats. Despite numerous passive algorithms that have been attempted to thwart malicious Deepfake…

Watermarking is a principled approach for tracing the provenance of large language model (LLM) outputs, but its deployment in practice is hindered by inference inefficiency. Speculative sampling accelerates inference, with efficiency…

The increasing use of Large Language Models (LLMs) for generating highly coherent and contextually relevant text introduces new risks, including misuse for unethical purposes such as disinformation or academic dishonesty. To address these…

The widespread deployment of high-fidelity generative models has intensified the need for reliable mechanisms for provenance and content authentication. In-processing watermarking, embedding a signature into the generative model's synthesis…

As Large Language Models (LLMs) become increasingly sophisticated, they raise significant security concerns, including the creation of fake news and academic misuse. Most detectors for identifying model-generated text are limited by their…

Random Linear Network Coding (RLNC) provides a theoretically efficient method for coding. Some of its practical drawbacks are the complexity of decoding and the overhead due to the coding vectors. For computationally weak and battery-driven…

In recent trends, one can observe Large Language Models (LLMs) are exposed to backdoor attacks where vicious triggers added during training or model editing to elicit harmful outputs on specific input patterns while maintaining clean…

Watermarking has emerged as a promising technique to track AI-generated content and differentiate it from authentic human creations. While prior work extensively studies watermarking for autoregressive large language models (LLMs) and image…

The widely adopted and powerful generative large language models (LLMs) have raised concerns about intellectual property rights violations and the spread of machine-generated misinformation. Watermarking serves as a promising approch to…

The task of discerning between generated and natural texts is increasingly challenging. In this context, watermarking emerges as a promising technique for ascribing generated text to a specific model. It alters the sampling generation…

While existing audio watermarking techniques have achieved strong robustness against traditional digital signal processing (DSP) attacks, they remain vulnerable to neural resynthesis. This occurs because modern neural audio codecs act as…

Watermarking the outputs of generative models has emerged as a promising approach for tracking their provenance. Despite significant interest in autoregressive image generation models and their potential for misuse, no prior work has…

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels…

Generation-time text watermarking embeds statistical signals into text for traceability of AI-generated content. We explore *post-hoc watermarking* where an LLM rewrites existing text while applying generation-time watermarking, to protect…

Large language models (LLMs) can be trained or fine-tuned on data obtained without the owner's consent. Verifying whether a specific LLM was trained on particular data instances or an entire dataset is extremely challenging. Dataset…

We present SWaRL, a robust and fidelity-preserving watermarking framework designed to protect the intellectual property of code LLMs by embedding unique and verifiable signatures in the generated program. Existing watermarking approaches…