相关论文: Locking Down the Finetuned LLMs Safety

As the number of large language models (LLMs) released to the public grows, there is a pressing need to understand the safety implications associated with these models learning from third-party custom finetuning data. We explore the…

Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…

Large Language Models (LLMs) have exhibited great performance in autonomously calling various tools in external environments, leading to better problem solving and task automation capabilities. However, these external tools also amplify…

Robust alignment guardrails for large language models (LLMs) are becoming increasingly important with their widespread application. In contrast to previous studies, we demonstrate that inference-time activation interventions can bypass…

With the widespread use of multi-modal Large Language models (MLLMs), safety issues have become a growing concern. Multi-turn dialogues, which are more common in everyday interactions, pose a greater risk than single prompts; however,…

Safety guardrails in large language models (LLMs) are a critical component in preventing harmful outputs. Yet, their resilience under perturbation remains poorly understood. In this paper, we investigate the robustness of safety fine-tuning…

The last two years have seen a rapid growth in concerns around the safety of large language models (LLMs). Researchers and practitioners have met these concerns by creating an abundance of datasets for evaluating and improving LLM safety.…

Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks. Nevertheless, they still pose notable safety risks due to potential misuse for malicious purposes. Jailbreaking, which seeks to induce models to…

Fine-tuning Large Language Models (LLMs) with Low-Rank Adaptation (LoRA) enhances adaptability while reducing computational costs. However, fine-tuning can compromise safety alignment, even with benign data, increasing susceptibility to…

This paper presents a systematic evaluation of Large Language Models' (LLMs) behavior on long-tail distributed (encrypted) texts and their safety implications. We introduce a two-dimensional framework for assessing LLM safety: (1)…

Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak defenses. Current defense methods rely on costly fine-tuning…

Machine learning is advancing rapidly, with applications bringing notable benefits, such as improvements in translation and code generation. Models like ChatGPT, powered by Large Language Models (LLMs), are increasingly integrated into…

Safety alignment has become a critical step to ensure LLMs refuse harmful requests while providing helpful and harmless responses. However, despite the ubiquity of safety alignment for deployed frontier models, two separate lines of recent…

Large language models (LLMs) are increasingly deployed behind safety guardrails such as system prompts and content filters, especially in settings where product teams cannot modify model weights. In practice these guardrails are typically…

Large Language Models (LLMs) have demonstrated exceptional performance across various tasks, but their security vulnerabilities can be exploited by attackers to generate harmful content, causing adverse impacts across various societal…

Large vision-language models (LVLMs) have achieved remarkable progress in vision-language reasoning tasks, yet ensuring their safety remains a critical challenge. Recent input-side defenses detect unsafe images with CLIP and prepend safety…

Fine-tuning is an essential and pervasive functionality for applying large language models (LLMs) to downstream tasks. However, it has the potential to substantially degrade safety alignment, e.g., by greatly increasing susceptibility to…

While fine-tuning services drive the rapid expansion of task capabilities in large language models (LLMs), they are often accompanied by the degradation and reorganization of safety-aligned representations, making models more prone to…

Large Language Models (LLMs) have been extensively used across diverse domains, including virtual assistants, automated code generation, and scientific research. However, they remain vulnerable to jailbreak attacks, which manipulate the…

Fine-tuning large language models (LLMs) to adapt to evolving safety policies is costly and impractical. Mechanistic interpretability enables inference-time control through latent activation steering, yet its potential for precise,…