Peng Ding


2024

pdf
A Wolf in Sheep’s Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily
Peng Ding | Jun Kuang | Dan Ma | Xuezhi Cao | Yunsen Xian | Jiajun Chen | Shujian Huang
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)

Large Language Models (LLMs), such as ChatGPT and GPT-4, are designed to provide useful and safe responses. However, adversarial prompts known as ‘jailbreaks’ can circumvent safeguards, leading LLMs to generate potentially harmful content. Exploring jailbreak prompts can help to better reveal the weaknesses of LLMs and further steer us to secure them. Unfortunately, existing jailbreak methods either suffer from intricate manual design or require optimization on other white-box models, which compromises either generalization or efficiency. In this paper, we generalize jailbreak prompt attacks into two aspects: (1) Prompt Rewriting and (2) Scenario Nesting. Based on this, we propose ReNeLLM, an automatic framework that leverages LLMs themselves to generate effective jailbreak prompts. Extensive experiments demonstrate that ReNeLLM significantly improves the attack success rate while greatly reducing the time cost compared to existing baselines. Our study also reveals the inadequacy of current defense methods in safeguarding LLMs. Finally, we analyze the failure of LLMs defense from the perspective of prompt execution priority, and propose corresponding defense strategies. We hope that our research can catalyze both the academic community and LLMs developers towards the provision of safer and more regulated LLMs. The code is available at https://github.com/NJUNLP/ReNeLLM.

2018

pdf
YNU_Deep at SemEval-2018 Task 11: An Ensemble of Attention-based BiLSTM Models for Machine Comprehension
Peng Ding | Xiaobing Zhou
Proceedings of the 12th International Workshop on Semantic Evaluation

We firstly use GloVe to learn the distributed representations automatically from the instance, question and answer triples. Then an attentionbased Bidirectional LSTM (BiLSTM) model is used to encode the triples. We also perform a simple ensemble method to improve the effectiveness of our model. The system we developed obtains an encouraging result on this task. It achieves the accuracy 0.7472 on the test set. We rank 5th according to the official ranking.

pdf
YNU Deep at SemEval-2018 Task 12: A BiLSTM Model with Neural Attention for Argument Reasoning Comprehension
Peng Ding | Xiaobing Zhou
Proceedings of the 12th International Workshop on Semantic Evaluation

This paper describes the system submitted to SemEval-2018 Task 12 (The Argument Reasoning Comprehension Task). Enabling a computer to understand a text so that it can answer comprehension questions is still a challenging goal of NLP. We propose a Bidirectional LSTM (BiLSTM) model that reads two sentences separated by a delimiter to determine which warrant is correct. We extend this model with a neural attention mechanism that encourages the model to make reasoning over the given claims and reasons. Officially released results show that our system ranks 6th among 22 submissions to this task.

2017

pdf
YNUDLG at IJCNLP-2017 Task 5: A CNN-LSTM Model with Attention for Multi-choice Question Answering in Examinations
Min Wang | Qingxun Liu | Peng Ding | Yongbin Li | Xiaobing Zhou
Proceedings of the IJCNLP 2017, Shared Tasks

In this paper, we perform convolutional neural networks (CNN) to learn the joint representations of question-answer pairs first, then use the joint representations as the inputs of the long short-term memory (LSTM) with attention to learn the answer sequence of a question for labeling the matching quality of each answer. We also incorporating external knowledge by training Word2Vec on Flashcards data, thus we get more compact embedding. Experimental results show that our method achieves better or comparable performance compared with the baseline system. The proposed approach achieves the accuracy of 0.39, 0.42 in English valid set, test set, respectively.