Have You Merged My Model? On The Robustness of Large Language Model IP Protection Methods Against Model Merging

Model merging is a promising lightweight model empowerment technique that does not rely on expensive computing devices (e.g., GPUs) or require the collection of specific training data. Instead, it involves editing different upstream model parameters to absorb their downstream task capabilities. However, uncertified model merging can infringe upon the Intellectual Property (IP) rights of the original upstream models. In this paper, we conduct the first study on the robustness of IP protection methods in model merging scenarios. We investigate two state-of-the-art IP protection techniques: Quantization Watermarking and Instructional Fingerprint, along with various advanced model merging technologies, such as Task Arithmetic, TIES-MERGING, and so on. Experimental results indicate that current Large Language Model (LLM) watermarking techniques cannot survive in the merged models, whereas model fingerprinting techniques can. Our research aims to highlight that model merging should be an indispensable consideration in the robustness assessment of model IP protection techniques, thereby promoting the healthy development of the open-source LLM community.

FigStep: Jailbreaking Large Vision-language Models via Typographic Visual Prompts

Large vision-language models (VLMs) like GPT-4V represent an unprecedented revolution in the field of artificial intelligence (AI). Compared to single-modal large language models (LLMs), VLMs possess more versatile capabilities by incorporating additional modalities (e.g., images). Meanwhile, there's a rising enthusiasm in the AI community to develop open-source VLMs, such as LLaVA and MiniGPT4, which, however, have not undergone rigorous safety assessment. In this paper, to demonstrate that more modalities lead to unforeseen AI safety issues, we propose FigStep, a novel jailbreaking framework against VLMs. FigStep feeds harmful instructions into VLMs through the image channel and then uses benign text prompts to induce VLMs to output contents that violate common AI safety policies. Our experimental results show that FigStep can achieve an average attack success rate of 94.8% across 2 families of popular open-source VLMs, LLaVA and MiniGPT4 (a total of 5 VLMs). Moreover, we demonstrate that the methodology of FigStep can even jailbreak GPT-4V, which already leverages several system-level mechanisms to filter harmful queries. Above all, our experimental results reveal that VLMs are vulnerable to jailbreaking attacks, which highlights the necessity of novel safety alignments between visual and textual modalities.

SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders

Self-supervised learning is an emerging machine learning (ML) paradigm. Compared to supervised learning that leverages high-quality labeled datasets to achieve good performance, self-supervised learning relies on unlabeled datasets to pre-train powerful encoders which can then be treated as feature extractors for various downstream tasks. The huge amount of data and computational resources consumption makes the encoders themselves become a valuable intellectual property of the model owner. Recent research has shown that the ML model's copyright is threatened by model stealing attacks, which aims to train a surrogate model to mimic the behavior of a given model. We empirically show that pre-trained encoders are highly vulnerable to model stealing attacks. However, most of the current efforts of copyright protection algorithms such as fingerprinting and watermarking concentrate on classifiers. Meanwhile, the intrinsic challenges of pre-trained encoder's copyright protection remain largely unstudied. We fill the gap by proposing SSLGuard, the first watermarking algorithm for pre-trained encoders. Given a clean pre-trained encoder, SSLGuard embeds a watermark into it and outputs a watermarked version. The shadow training technique is also applied to preserve the watermark under potential model stealing attacks. Our extensive evaluation shows that SSLGuard is effective in watermark injection and verification, and is robust against model stealing and other watermark removal attacks such as pruning and finetuning.