Blind Spot Navigation: Evolutionary Discovery of Sensitive Semantic Concepts for LVLMs
Authors: Zihao Pan, Yu Tong, Weibin Wu, Jingyi Wang, Lifeng Chen, Zhe Zhao, Jiajia Wei, Yitong Qiao, Zibin Zheng | Published: 2025-05-21
Prompt leaking
Adaptive Plan-Execute Framework for Smart Contract Security Auditing
Authors: Zhiyuan Wei, Jing Sun, Zijian Zhang, Zhe Hou, Zixiao Zhao | Published: 2025-05-21 | Updated: 2025-05-22
Fragments to Facts: Partial-Information Fragment Inference from LLMs
Authors: Lucas Rosenblatt, Bin Han, Robert Wolfe, Bill Howe | Published: 2025-05-20
R1dacted: Investigating Local Censorship in DeepSeek’s R1 Language Model
Authors: Ali Naseh, Harsh Chaudhari, Jaechul Roh, Mingshi Wu, Alina Oprea, Amir Houmansadr | Published: 2025-05-19
Cutting Through Privacy: A Hyperplane-Based Data Reconstruction Attack in Federated Learning
Authors: Francesco Diana, André Nusser, Chuan Xu, Giovanni Neglia | Published: 2025-05-15
Instantiating Standards: Enabling Standard-Driven Text TTP Extraction with Evolvable Memory
Authors: Cheng Meng, ZhengWei Jiang, QiuYun Wang, XinYi Li, ChunYan Ma, FangMing Dong, FangLi Ren, BaoXu Liu | Published: 2025-05-14
SecReEvalBench: A Multi-turned Security Resilience Evaluation Benchmark for Large Language Models
Authors: Huining Cui, Wei Liu | Published: 2025-05-12
I Know What You Said: Unveiling Hardware Cache Side-Channels in Local Large Language Model Inference
Authors: Zibo Gao, Junjie Hu, Feng Guo, Yixin Zhang, Yinglong Han, Siyuan Liu, Haiyang Li, Zhiqiang Lv | Published: 2025-05-10 | Updated: 2025-05-14
LLM-Text Watermarking based on Lagrange Interpolation
Authors: Jarosław Janas, Paweł Morawiecki, Josef Pieprzyk | Published: 2025-05-09 | Updated: 2025-05-13
Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks
Authors: Yixin Cheng, Hongcheng Guo, Yangming Li, Leonid Sigal | Published: 2025-05-08