Related papers: IMMA: Immunizing text-to-image Models against Mali…

Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradigm introduces a previously underexplored attack surface,…

Large language models (LLMs) are popular for high-quality text generation but can produce harmful content, even when aligned with human values through reinforcement learning. Adversarial prompts can bypass their safety measures. We propose…

Current Large Language Models (LLMs), even those tuned for safety and alignment, are susceptible to jailbreaking. Some have found that just further fine-tuning an aligned model with benign data (i.e., data without harmful content)…

Customizing Large Language Models (LLMs) on untrusted datasets poses severe risks of injecting toxic behaviors. In this work, we introduce Optimus, a novel defense framework designed to mitigate fine-tuning harms while preserving…

With the widespread deployment of Multimodal Large Language Models (MLLMs) for visual-reasoning tasks, improving their safety has become crucial. Recent research indicates that despite training-time safety alignment, these models remain…

Open-source Large Language Models (LLMs) often employ safety alignment methods to resist harmful instructions. However, recent research shows that maliciously fine-tuning these LLMs on harmful data can easily bypass these safeguards. To…

Open-weight AI systems offer unique benefits, including enhanced transparency, open research, and decentralized access. However, they are vulnerable to tampering attacks which can efficiently elicit harmful behaviors by modifying weights or…

Model immunization is an emerging direction that aims to mitigate the potential risk of misuse associated with open-sourced models and advancing adaptation methods. The idea is to make the released models' weights difficult to fine-tune on…

We explore a knowledge sanitization approach to mitigate the privacy concerns associated with large language models (LLMs). LLMs trained on a large corpus of Web data can memorize and potentially reveal sensitive or confidential…

Fine-tuning language models has become increasingly popular following the proliferation of open models and improvements in cost-effective parameter efficient fine-tuning. However, fine-tuning can influence model properties such as safety.…

Large Language Models (LLMs) can be misused to spread unwanted content at scale. Content watermarking deters misuse by hiding messages in content, enabling its detection using a secret watermarking key. Robustness is a core security…

Vision-Language Models (VLMs) are increasingly susceptible to sophisticated adversarial attacks, including adaptive strategies specifically designed to bypass existing defenses. To address this vulnerability, we propose MirrorCheck, a…

Current image generation models can effortlessly produce high-quality, highly realistic images, but this also increases the risk of misuse. In various Text-to-Image or Image-to-Image tasks, attackers can generate a series of images…

Recent generative large language models (LLMs) show remarkable performance in non-English languages, but when prompted in those languages they tend to express higher harmful social biases and toxicity levels. Prior work has shown that…

Large language models (LLMs) have transformed natural language processing, but their ability to memorize training data poses significant privacy risks. This paper investigates model inversion attacks on the Llama 3.2 model, a multilingual…

The commercialization of text-to-image diffusion models (DMs) brings forth potential copyright concerns. Despite numerous attempts to protect DMs from copyright issues, the vulnerabilities of these solutions are underexplored. In this…

Text-to-image diffusion models can generate diverse content with flexible prompts, which makes them well-suited for customization through fine-tuning with a small amount of user-provided data. However, controllable fine-tuning that prevents…

Fine-tuning is a common and effective method for tailoring large language models (LLMs) to specialized tasks and applications. In this paper, we study the privacy implications of fine-tuning LLMs on user data. To this end, we consider a…

Digital images are vulnerable to nefarious tampering attacks such as content addition or removal that severely alter the original meaning. It is somehow like a person without protection that is open to various kinds of viruses. Image…

Multi-modal foundation models combining vision and language models such as Flamingo or GPT-4 have recently gained enormous interest. Alignment of foundation models is used to prevent models from providing toxic or harmful output. While…