Yang Liu

Xunguang Wang, Daoyuan Wu, Zhenlan Ji et al.

Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generation-based, and the recent indirect and multilingual jailbreaks. However, delivering a practical jailbreak defense is challenging because it needs to not only handle all the above jailbreak attacks but also incur negligible delays to user prompts, as well as be compatible with both open-source and closed-source LLMs. Inspired by how the traditional security concept of shadow stacks defends against memory overflow attacks, this paper introduces a generic LLM jailbreak defense framework called SelfDefend, which establishes a shadow LLM as a defense instance (in detection state) to concurrently protect the target LLM instance (in normal answering state) in the normal stack and collaborate with it for checkpoint-based access control. The effectiveness of SelfDefend builds upon our observation that existing LLMs can identify harmful prompts or intentions in user queries, which we empirically validate using mainstream GPT-3.5/4 models against major jailbreak attacks. To further improve the defense's robustness and minimize costs, we employ a data distillation approach to tune dedicated open-source defense models. When deployed to protect GPT-3.5/4, Claude, Llama-2-7b/13b, and Mistral, these models outperform seven state-of-the-art defenses and match the performance of GPT-4-based SelfDefend, with significantly lower extra delays. Further experiments show that the tuned models are robust to adaptive jailbreaks and prompt injections.

Ze Chen, Gongyu Zhang, Jiayu Huo et al.

This study introduces a novel framework for enhancing domain generalization in medical imaging, specifically focusing on utilizing unlabelled multi-view colour fundus photographs. Unlike traditional approaches that rely on single-view imaging data and face challenges in generalizing across diverse clinical settings, our method leverages the rich information in the unlabelled multi-view imaging data to improve model robustness and accuracy. By incorporating a class balancing method, a test-time adaptation technique and a multi-view optimization strategy, we address the critical issue of domain shift that often hampers the performance of machine learning models in real-world applications. Experiments comparing various state-of-the-art domain generalization and test-time optimization methodologies show that our approach consistently outperforms when combined with existing baseline and state-of-the-art methods. We also show our online method improves all existing techniques. Our framework demonstrates improvements in domain generalization capabilities and offers a practical solution for real-world deployment by facilitating online adaptation to new, unseen datasets. Our code is available at https://github.com/zgy600/RetiGen .

Zheng Zhang, Fan Yang, Ziyan Jiang et al. · amazon-science

Recent advances in large language models (LLMs) have enhanced their ability to process long input contexts. This development is particularly crucial for tasks that involve retrieving knowledge from an external datastore, which can result in long inputs. However, recent studies show a positional bias in LLMs, demonstrating varying performance depending on the location of useful information within the input sequence. In this study, we conduct extensive experiments to investigate the root causes of positional bias. Our findings indicate that the primary contributor to LLM positional bias stems from the inherent positional preferences of different models. We demonstrate that merely employing prompt-based solutions is inadequate for overcoming the positional preferences. To address this positional bias issue of a pre-trained LLM, we developed a Position-Aware Parameter Efficient Fine-Tuning (PAPEFT) approach which is composed of a data augmentation technique and a parameter efficient adapter, enhancing a uniform attention distribution across the input context. Our experiments demonstrate that the proposed approach effectively reduces positional bias, improving LLMs' effectiveness in handling long context sequences for various tasks that require externally retrieved knowledge.