6 citations · 27 across the 15 of their papers we have counts for
15 papers
Comprehensive Vulnerability Analysis is Necessary for Trustworthy LLM-MAS
Pengfei He, Yue Xing, Juanhui Li +7
TThis paper argues that \textbf{a comprehensive vulnerability analysis is essential for building trustworthy Large Language Model-based Multi-Agent Systems (LLM-MAS)}. These system…
Multi-Faceted Studies on Data Poisoning can Advance LLM Development
Pengfei He, Yue Xing, Han Xu +2
The lifecycle of large language models (LLMs) is far more complex than that of traditional machine learning models, involving multiple training stages, diverse data sources, and va…
Red-Teaming LLM Multi-Agent Systems via Communication Attacks
Pengfei He, Yupin Lin, Shen Dong +3
Large Language Model-based Multi-Agent Systems (LLM-MAS) have revolutionized complex problem-solving capability by enabling sophisticated agent collaboration through message-based…
Towards the Effect of Examples on In-Context Learning: A Theoretical Case Study
Pengfei He, Yingqian Cui, Han Xu +4
In-context learning (ICL) has emerged as a powerful capability for large language models (LLMs) to adapt to downstream tasks by leveraging a few (demonstration) examples. Despite i…
Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data
Shenglai Zeng, Jiankun Zhang, Pengfei He +7
Retrieval-augmented generation (RAG) enhances the outputs of language models by integrating relevant information retrieved from external knowledge sources. However, when the retrie…
Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis
Yuping Lin, Pengfei He, Han Xu +4
Large language models (LLMs) are susceptible to a type of attack known as jailbreaking, which misleads LLMs to output harmful contents. Although there are diverse jailbreak attack…
Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention
Jie Ren, Yaxin Li, Shenglai Zeng +4
Recent advancements in text-to-image diffusion models have demonstrated their remarkable capability to generate high-quality images from textual prompts. However, increasing resear…
The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)
Shenglai Zeng, Jiankun Zhang, Pengfei He +8
Retrieval-augmented generation (RAG) is a powerful technique to facilitate language model with proprietary and private data, where data privacy is a pivotal concern. Whereas extens…
Copyright Protection in Generative AI: A Technical Perspective
Jie Ren, Han Xu, Pengfei He +10
Generative AI has witnessed rapid advancement in recent years, expanding their capabilities to create synthesized content such as text, images, audio, and code. The high fidelity a…
Data Poisoning for In-context Learning
Pengfei He, Han Xu, Yue Xing +3
In the domain of large language models (LLMs), in-context learning (ICL) has been recognized for its innovative ability to adapt to new tasks, relying on examples rather than retra…
A Robust Semantics-based Watermark for Large Language Model against Paraphrasing
Jie Ren, Han Xu, Yiding Liu +4
Large language models (LLMs) have show great ability in various natural language tasks. However, there are concerns that LLMs are possible to be used improperly or even illegally.…
On the Generalization of Training-based ChatGPT Detection Methods
Han Xu, Jie Ren, Pengfei He +5
ChatGPT is one of the most popular language models which achieve amazing performance on various natural language tasks. Consequently, there is also an urgent need to detect the tex…
Exploring Memorization in Fine-tuned Language Models
Shenglai Zeng, Yaxin Li, Jie Ren +7
Large language models (LLMs) have shown great capabilities in various tasks but also exhibited memorization of training data, raising tremendous privacy and copyright concerns. Whi…
Stealthy Backdoor Attack via Confidence-driven Sampling
Pengfei He, Yue Xing, Han Xu +6
Backdoor attacks aim to surreptitiously insert malicious triggers into DNN models, granting unauthorized control during testing scenarios. Existing methods lack robustness against…
FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models
Yingqian Cui, Jie Ren, Yuping Lin +7
Text-to-image generative models, especially those based on latent diffusion models (LDMs), have demonstrated outstanding ability in generating high-quality and high-resolution imag…