Feint and Attack: Attention-Based Strategies for Jailbreaking and Protecting LLMs
Authors: Rui Pu, Chaozhuo Li, Rui Ha, Zejian Chen, Litian Zhang, Zheng Liu, Lirong Qiu, Zaisheng Ye | Published: 2024-10-18 | Updated: 2025-07-08
プロンプトインジェクション
Denial-of-Service Poisoning Attacks against Large Language Models
Authors: Kuofeng Gao, Tianyu Pang, Chao Du, Yong Yang, Shu-Tao Xia, Min Lin | Published: 2024-10-14
On Calibration of LLM-based Guard Models for Reliable Content Moderation
Authors: Hongfu Liu, Hengguan Huang, Hao Wang, Xiangming Gu, Ye Wang | Published: 2024-10-14
Can LLMs be Scammed? A Baseline Measurement Study
Authors: Udari Madhushani Sehwag, Kelly Patel, Francesca Mosca, Vineeth Ravi, Jessica Staddon | Published: 2024-10-14
Survival of the Safest: Towards Secure Prompt Optimization through Interleaved Multi-Objective Evolution
Authors: Ankita Sinha, Wendi Cui, Kamalika Das, Jiaxin Zhang | Published: 2024-10-12
Can a large language model be a gaslighter?
Authors: Wei Li, Luyao Zhu, Yang Song, Ruixi Lin, Rui Mao, Yang You | Published: 2024-10-11
F2A: An Innovative Approach for Prompt Injection by Utilizing Feign Security Detection Agents
Authors: Yupeng Ren | Published: 2024-10-11 | Updated: 2024-10-14
PILLAR: an AI-Powered Privacy Threat Modeling Tool
Authors: Majid Mollaeefar, Andrea Bissoli, Silvio Ranise | Published: 2024-10-11
APOLLO: A GPT-based tool to detect phishing emails and generate explanations that warn users
Authors: Giuseppe Desolda, Francesco Greco, Luca Viganò | Published: 2024-10-10
Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy
Authors: Tong Wu, Shujian Zhang, Kaiqiang Song, Silei Xu, Sanqiang Zhao, Ravi Agrawal, Sathish Reddy Indurthi, Chong Xiang, Prateek Mittal, Wenxuan Zhou | Published: 2024-10-09