Related papers: Disappearing Ink: Obfuscation Breaks N-gram Code W…

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…

JavaScript obfuscators are widely deployed to protect intellectual property and resist reverse engineering, yet their correctness has been largely overlooked compared to performance and resilience. Existing evaluations typically measure…

Watermarking combines an imperceptible change to an input image that will trigger a detector, to assert provenance and protect intellectual property. The literature has shown great interest in attacks on watermarking schemes: attackers are…

Trigger set-based watermarking schemes have gained emerging attention as they provide a means to prove ownership for deep neural network model owners. In this paper, we argue that state-of-the-art trigger set-based watermarking algorithms…

As the web moves away from stateful tracking, browser fingerprinting is becoming more prevalent. Unfortunately, existing approaches to detect browser fingerprinting do not take into account potential evasion tactics such as code…

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…

Watermarking diffusion-generated images is crucial for copyright protection and user tracking. However, current diffusion watermarking methods face significant limitations: zero-bit watermarking systems lack the capacity for large-scale…

Plagiarism in programming assignments is a persistent issue in computer science education, increasingly complicated by the emergence of automated obfuscation attacks. While software plagiarism detectors are widely used to identify…

Recent advances in large language models have raised wide concern in generating abundant plausible source code without scrutiny, and thus tracing the provenance of code emerges as a critical issue. To solve the issue, we propose CodeMark, a…

In recent years, there has been significant advancement in the field of model watermarking techniques. However, the protection of image-processing neural networks remains a challenge, with only a limited number of methods being developed.…

Natural language generation (NLG) applications have gained great popularity due to the powerful deep learning techniques and large training corpus. The deployed NLG models may be stolen or used without authorization, while watermarking has…

As AI advances, copyrighted content faces growing risk of unauthorized use, whether through model training or direct misuse. Building upon invisible adversarial perturbation, recent works developed copyright protections against specific AI…

The rapid advancement of generative AI has underscored the critical need for identifying image ownership and protecting copyrights. This makes post-processing image watermarking an essential tool -- it involves embedding a specific…

Understanding code represents a core ability needed for automating software development tasks. While foundation models like LLMs show impressive results across many software engineering challenges, the extent of their true semantic…

In today's digital landscape, the blending of AI-generated and authentic content has underscored the need for copyright protection and content authentication. Watermarking has become a vital tool to address these challenges, safeguarding…

LLM watermarks stand out as a promising way to attribute ownership of LLM-generated text. One threat to watermark credibility comes from spoofing attacks, where an unauthorized third party forges the watermark, enabling it to falsely…

Watermarking has emerged as a promising technique for detecting texts generated by LLMs. Current research has primarily focused on three design criteria: high quality of the watermarked text, high detectability, and robustness against…

A recent watermarking scheme for language models achieves distortion-free embedding and robustness to edit-distance attacks. However, it suffers from limited generation diversity and high detection overhead. In parallel, recent research has…

Protecting source code against reverse engineering and theft is an important problem. The goal is to carry out computations using confidential algorithms on an untrusted party while ensuring confidentiality of algorithms. This problem has…

We study the problem of watermarking large language models (LLMs) generated text -- one of the most promising approaches for addressing the safety challenges of LLM usage. In this paper, we propose a rigorous theoretical framework to…