相关论文: Locking Down the Finetuned LLMs Safety

Ensuring robust safety alignment while preserving utility is critical for the reliable deployment of Large Language Models (LLMs). However, current techniques fundamentally suffer from intertwined deficiencies: insufficient robustness…

Organizations are increasingly adopting and adapting Large Language Models (LLMs) hosted on public repositories such as HuggingFace. Although these adaptations often improve performance on specialized downstream tasks, recent evidence…

Mechanistic interpretability reveals that safety-critical behaviors (e.g., alignment, jailbreak, backdoor) in Large Language Models (LLMs) are grounded in specialized functional components. However, existing safety attribution methods…

Large Language Models (LLMs) are known to be susceptible to crafted adversarial attacks or jailbreaks that lead to the generation of objectionable content despite being aligned to human preferences using safety fine-tuning methods. While…

Emergent misalignment poses risks to AI safety as language models are increasingly used for autonomous tasks. In this paper, we present a population of large language models (LLMs) fine-tuned on insecure datasets spanning 11 diverse…

Large visual language models (LVLMs) have demonstrated excellent instruction-following capabilities, yet remain vulnerable to stealthy backdoor attacks when finetuned using contaminated data. Existing backdoor defense techniques are usually…

Despite the intrinsic risk-awareness of Large Language Models (LLMs), current defenses often result in shallow safety alignment, rendering models vulnerable to disguised attacks (e.g., prefilling) while degrading utility. To bridge this…

Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled…

Finetuning large language models (LLMs) enables user-specific customization but introduces critical safety risks: even a few harmful examples can compromise safety alignment. A common mitigation strategy is to update the model more strongly…

The safety of Large Language Models (LLMs) has gained increasing attention in recent years, but there still lacks a comprehensive approach for detecting safety issues within LLMs' responses in an aligned, customizable and explainable…

Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we highlight an insidious safety threat: a compromised LLM can…

Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and over-refusal of benign queries due to rigid safety mechanisms. These issues are further complicated…

Safety alignment of Large Language Models (LLMs) has recently become a critical objective of model developers. In response, a growing body of work has been investigating how safety alignment can be bypassed through various jailbreaking…

Fine-tuning text-to-image diffusion models is widely used for personalization and adaptation for new domains. In this paper, we identify a critical vulnerability of fine-tuning: safety alignment methods designed to filter harmful content…

Fine-tuning Large Language Models (LLMs) on some task-specific datasets has been a primary use of LLMs. However, it has been empirically observed that this approach to enhancing capability inevitably compromises safety, a phenomenon also…

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…

The widespread deployment of large language models (LLMs) across linguistic communities necessitates reliable multilingual safety alignment. However, recent efforts to extend alignment to other languages often require substantial resources,…

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)…

Recent advancements in model architectures and length extrapolation techniques have significantly extended the context length of large language models (LLMs), paving the way for their application in increasingly complex tasks. However,…

Large language models (LLMs) have a transformative impact on a variety of scientific tasks across disciplines including biology, chemistry, medicine, and physics. However, ensuring the safety alignment of these models in scientific research…