Related papers: Aligned but Fragile: Enhancing LLM Safety Robustne…

Recent work has shown that fine-tuning large language models (LLMs) on code with security vulnerabilities can result in misaligned and unsafe behaviors across broad domains. These results prompted concerns about the emergence of harmful…

Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily removed by fine-tuning with a few adversarially chosen…

Zeroth-order optimizers have recently emerged as a practical approach for fine-tuning large language models (LLMs), significantly reducing GPU memory consumption compared to traditional first-order methods. Yet, existing zeroth-order…

Large language models (LLMs) have demonstrated revolutionary capabilities in understanding complex contexts and performing a wide range of tasks. However, LLMs can also answer questions that are unethical or harmful, raising concerns about…

While large language models (LLMs) such as Llama-2 or GPT-4 have shown impressive zero-shot performance, fine-tuning is still necessary to enhance their performance for customized datasets, domain-specific tasks, or other private needs.…

Large language models (LLMs) show inherent brittleness in their safety mechanisms, as evidenced by their susceptibility to jailbreaking and even non-malicious fine-tuning. This study explores this brittleness of safety alignment by…

Although large language models (LLMs) achieve effective safety alignment at the time of release, they still face various safety challenges. A key issue is that fine-tuning often compromises the safety alignment of LLMs. To address this…

Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models (LLMs). However,…

Misaligned research objectives have considerably hindered progress in adversarial robustness research over the past decade. For instance, an extensive focus on optimizing target metrics, while neglecting rigorous standardized evaluation,…

Large language models (LLMs) have achieved remarkable success across many applications, but their ability to generate harmful content raises serious safety concerns. Although safety alignment techniques are often applied during pre-training…

As advancements in large language models (LLMs) continue and the demand for personalized models increases, parameter-efficient fine-tuning (PEFT) methods (e.g., LoRA) will become essential due to their efficiency in reducing computation…

Fine-tuning Large Language Models (LLMs) typically involves either full fine-tuning, which updates all model parameters, or Parameter-Efficient Fine-Tuning (PEFT), which adjusts a small subset of parameters. However, both approaches have…

Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation…

Existing training-time safety alignment techniques for large language models (LLMs) remain vulnerable to jailbreak attacks. Direct preference optimization (DPO), a widely deployed alignment method, exhibits limitations in both experimental…

With the increasing adoption of Large Language Models (LLMs), more customization is needed to ensure privacy-preserving and safe generation. We address this objective from two critical aspects: unlearning of sensitive information and…

Current safety alignment techniques for large language models (LLMs) face two key challenges: (1) under-generalization, which leaves models vulnerable to novel jailbreak attacks, and (2) over-alignment, which leads to the excessive refusal…

Large Language Models (LLMs) are increasingly adopted in high-stakes scenarios, yet their safety mechanisms often remain fragile. Simple jailbreak prompts or even benign fine-tuning can bypass these protocols, underscoring the need to…

Fine-tuning LLMs on benign data can still degrade alignment and adversarial robustness, yet direct analysis of the role of fine-tuning objectives in shaping these safety outcomes remain limited. We present a controlled comparison of six…

The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthiness, adversaries can exploit these techniques to undermine…

The safety mechanisms of large language models (LLMs) exhibit notable fragility, as even fine-tuning on datasets without harmful content may still undermine their safety capabilities. Meanwhile, existing safety alignment methods…