Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
Authors: Xiangming Gu, Xiaosen Zheng, Tianyu Pang, Chao Du, Qian Liu, Ye Wang, Jing Jiang, Min Lin | Published: 2024-02-13 | Updated: 2024-06-03
LLMセキュリティ
Pandora: Jailbreak GPTs by Retrieval Augmented Generation Poisoning
Authors: Gelei Deng, Yi Liu, Kailong Wang, Yuekang Li, Tianwei Zhang, Yang Liu | Published: 2024-02-13
Utilizing Large LanguageModels to Detect Privacy Leaks in Mini-App Code
Authors: Liming Jiang | Published: 2024-02-12
Sentinels of the Stream: Unleashing Large Language Models for Dynamic Packet Classification in Software Defined Networks — Position Paper
Authors: Shariq Murtuza | Published: 2024-02-10
In-Context Learning Can Re-learn Forbidden Tasks
Authors: Sophie Xhonneux, David Dobre, Jian Tang, Gauthier Gidel, Dhanya Sridhar | Published: 2024-02-08
Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia
Authors: Guangyu Shen, Siyuan Cheng, Kaiyuan Zhang, Guanhong Tao, Shengwei An, Lu Yan, Zhuo Zhang, Shiqing Ma, Xiangyu Zhang | Published: 2024-02-08
SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models
Authors: Lijun Li, Bowen Dong, Ruohui Wang, Xuhao Hu, Wangmeng Zuo, Dahua Lin, Yu Qiao, Jing Shao | Published: 2024-02-07 | Updated: 2024-06-07
Homograph Attacks on Maghreb Sentiment Analyzers
Authors: Fatima Zahra Qachfar, Rakesh M. Verma | Published: 2024-02-05
Detecting Scams Using Large Language Models
Authors: Liming Jiang | Published: 2024-02-05
Signed-Prompt: A New Approach to Prevent Prompt Injection Attacks Against LLM-Integrated Applications
Authors: Xuchen Suo | Published: 2024-01-15