Related papers: Blind PRNG Hijacking: An Undetectable Integrity-Pr…
Retrieval-Augmented Generation (RAG) has become an effective method for enhancing large language models (LLMs) with up-to-date knowledge. However, it poses a significant risk of IP infringement, as IP datasets may be incorporated into the…
With the widespread adoption of Large Language Models (LLMs), concerns about potential misuse have emerged. To this end, watermarking has been adapted to LLM, enabling a simple and effective way to detect and monitor generated text.…
Jailbreak attacks pose a serious threat to Large Language Models (LLMs) by bypassing their safety mechanisms. A truly advanced jailbreak is defined not only by its effectiveness but, more critically, by its stealthiness. However, existing…
We propose Easymark, a family of embarrassingly simple yet effective watermarks. Text watermarking is becoming increasingly important with the advent of Large Language Models (LLM). LLMs can generate texts that cannot be distinguished from…
We propose an imperceptible multi-bit text watermark embedded by paraphrasing with LLMs. We fine-tune a pair of LLM paraphrasers that are designed to behave differently so that their paraphrasing difference reflected in the text semantics…
Multi-agent LLM systems introduce a security risk in which sensitive information accessed by one agent can propagate through shared context and reappear in downstream outputs, even without explicit adversarial intent. We formalise this…
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…
Text watermarks in large language models (LLMs) are increasingly used to detect synthetic text, mitigating misuse cases like fake news and academic dishonesty. While existing watermarking detection techniques primarily focus on classifying…
Watermarking large language models (LLMs) is vital for preventing their misuse, including the fabrication of fake news, plagiarism, and spam. It is especially important to watermark LLM-generated code, as it often contains intellectual…
Text watermarking for large language models (LLMs) enables model owners to verify text origin and protect intellectual property. While watermarking methods for closed-source LLMs are relatively mature, extending them to open-source models…
The rapid advancement of Large Language Models (LLMs) has significantly enhanced the capabilities of text generators. With the potential for misuse escalating, the importance of discerning whether texts are human-authored or generated by…
The growing deployment of Large Language Models (LLMs) has raised concerns about their misuse in generating harmful or deceptive content. To address this issue, watermarking methods have been proposed to embed identifiable multi-bit…
The local news landscape, a vital source of reliable information for 28 million Americans, faces a growing threat from Pink Slime Journalism, a low-quality, auto-generated articles that mimic legitimate local reporting. Detecting these…
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…
Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieval, a two-stage data poisoning attack that hijacks RAG systems through adversarially…
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…
The evolution of Large Language Models (LLMs) into agentic systems that perform autonomous reasoning and tool use has created significant intellectual property (IP) value. We demonstrate that these systems are highly vulnerable to imitation…
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…
Watermarking generative models consists of planting a statistical signal (watermark) in a model's output so that it can be later verified that the output was generated by the given model. A strong watermarking scheme satisfies the property…
Digital watermarking enables protection against copyright infringement of images. Although existing methods embed watermarks imperceptibly and demonstrate robustness against attacks, they typically lack resilience against geometric…