Computing Optimization-Based Prompt Injections Against Closed-Weights Models By Misusing a Fine-Tuning API
Authors: Andrey Labunets, Nishit V. Pandya, Ashish Hooda, Xiaohan Fu, Earlence Fernandes | Published: 2025-01-16
プロンプトインジェクション
A Survey on Responsible LLMs: Inherent Risk, Malicious Use, and Mitigation Strategy
Authors: Huandong Wang, Wenjie Fu, Yingzhou Tang, Zhilong Chen, Yuxi Huang, Jinghua Piao, Chen Gao, Fengli Xu, Tao Jiang, Yong Li | Published: 2025-01-16
Unveiling Provider Bias in Large Language Models for Code Generation
Authors: Xiaoyu Zhang, Juan Zhai, Shiqing Ma, Qingshuang Bao, Weipeng Jiang, Chao Shen, Yang Liu | Published: 2025-01-14
Automating the Detection of Code Vulnerabilities by Analyzing GitHub Issues
Authors: Daniele Cipollone, Changjie Wang, Mariano Scazzariello, Simone Ferlin, Maliheh Izadi, Dejan Kostic, Marco Chiesa | Published: 2025-01-09
SpaLLM-Guard: Pairing SMS Spam Detection Using Open-source and Commercial LLMs
Authors: Muhammad Salman, Muhammad Ikram, Nardine Basta, Mohamed Ali Kaafar | Published: 2025-01-09
Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
Authors: Shiji Zhao, Ranjie Duan, Fengxiang Wang, Chi Chen, Caixin Kang, Jialing Tao, YueFeng Chen, Hui Xue, Xingxing Wei | Published: 2025-01-09
Exploring Large Language Models for Semantic Analysis and Categorization of Android Malware
Authors: Brandon J Walton, Mst Eshita Khatun, James M Ghawaly, Aisha Ali-Gombe | Published: 2025-01-08
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models
Authors: Lingzhi Yuan, Xinfeng Li, Chejian Xu, Guanhong Tao, Xiaojun Jia, Yihao Huang, Wei Dong, Yang Liu, XiaoFeng Wang, Bo Li | Published: 2025-01-07
RTLMarker: Protecting LLM-Generated RTL Copyright via a Hardware Watermarking Framework
Authors: Kun Wang, Kaiyan Chang, Mengdi Wang, Xinqi Zou, Haobo Xu, Yinhe Han, Ying Wang | Published: 2025-01-05
GNSS/GPS Spoofing and Jamming Identification Using Machine Learning and Deep Learning
Authors: Ali Ghanbarzade, Hossein Soleimani | Published: 2025-01-04