Related papers: LLM Fingerprinting via Semantically Conditioned Wa…
Model fingerprinting has emerged as a promising paradigm for claiming model ownership. However, robustness evaluations of these schemes have mostly focused on benign perturbations such as incremental fine-tuning, model merging, and…
Text watermarking has emerged as a pivotal technique for identifying machine-generated text. However, existing methods often rely on arbitrary vocabulary partitioning during decoding to embed watermarks, which compromises the availability…
Existing invasive (backdoor) fingerprints suffer from high-perplexity triggers that are easily filtered, fixed response patterns exposed by heuristic detectors, and spurious activations on benign inputs. We introduce \textsc{ForgetMark}, a…
Process mining is increasingly using textual information associated with events to tackle tasks such as anomaly detection and process discovery. Such semantics-aware process mining focuses on what behavior should be possible in a process…
Abuse of large language models reveals high risks as large language models are being deployed at an astonishing speed. It is important to protect the model weights to avoid malicious usage that violates licenses of open-source large…
In the era of costly pre-training of large language models, ensuring the intellectual property rights of model owners, and insuring that said models are responsibly deployed, is becoming increasingly important. To this end, we propose model…
Accurately quantifying uncertainty in large language models (LLMs) is crucial for their reliable deployment, especially in high-stakes applications. Current state-of-the-art methods for measuring semantic uncertainty in LLMs rely on strict…
Various watermarking methods (``watermarkers'') have been proposed to identify LLM-generated texts; yet, due to the lack of unified evaluation platforms, many critical questions remain under-explored: i) What are the strengths/limitations…
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…
Training data is a critical and often proprietary asset in Large Language Model (LLM) development, motivating the use of data watermarking to embed model-transferable signals for usage verification. We identify low coverage as a vital yet…
Although significant progress achieved, multi-label classification is still challenging due to the complexity of correlations among different labels. Furthermore, modeling the relationships between input and some (dull) classes further…
Large language models generate high-quality responses with potential misinformation, underscoring the need for regulation by distinguishing AI-generated and human-written texts. Watermarking is pivotal in this context, which involves…
Watermarking techniques offer a promising way to identify machine-generated content via embedding covert information into the contents generated from language models (LMs). However, the robustness of the watermarking schemes has not been…
As LLMs become commonplace, machine-generated text has the potential to flood the internet with spam, social media bots, and valueless content. Watermarking is a simple and effective strategy for mitigating such harms by enabling the…
Benchmark contamination poses a significant challenge to the reliability of Large Language Models (LLMs) evaluations, as it is difficult to assert whether a model has been trained on a test set. We introduce a solution to this problem by…
Safety mechanisms for large language models (LLMs) remain predominantly English-centric, creating systematic vulnerabilities in multilingual deployment. Prior work shows that translating malicious prompts into other languages can…
Model fingerprinting has emerged as a powerful tool for model owners to identify their shared model given API access. However, to lower false discovery rate, fight fingerprint leakage, and defend against coalitions of model users attempting…
Large language models (LLMs) face significant copyright and intellectual property challenges as the cost of training increases and model reuse becomes prevalent. While watermarking techniques have been proposed to protect model ownership,…
Watermarking of language model outputs enables statistical detection of model-generated text, which can mitigate harms and misuses of language models. Existing watermarking strategies operate by altering the decoder of an existing language…
With the rise of Machine Learning as a Service (MLaaS) platforms,safeguarding the intellectual property of deep learning models is becoming paramount. Among various protective measures, trigger set watermarking has emerged as a flexible and…