GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms
Authors: Sinan He, An Wang | Published: 2025-04-17
Malicious Code Detection in Smart Contracts via Opcode Vectorization
Authors: Huanhuan Zou, Zongwei Li, Xiaoqi Li | Published: 2025-04-17
Watermarking Needs Input Repetition Masking
Authors: David Khachaturov, Robert Mullins, Ilia Shumailov, Sumanth Dathathri | Published: 2025-04-16
zkVC: Fast Zero-Knowledge Proof for Private and Verifiable Computing
Authors: Yancheng Zhang, Mengxin Zheng, Xun Chen, Jingtong Hu, Weidong Shi, Lei Ju, Yan Solihin, Qian Lou | Published: 2025-04-16
バックドア攻撃
分類モデルに対するバックドア攻撃について解説します。
Secure Transfer Learning: Training Clean Models Against Backdoor in (Both) Pre-trained Encoders and Downstream Datasets
Authors: Yechao Zhang, Yuxuan Zhou, Tianyu Li, Minghui Li, Shengshan Hu, Wei Luo, Leo Yu Zhang | Published: 2025-04-16
The Evolution of Zero Trust Architecture (ZTA) from Concept to Implementation
Authors: Md Nasiruzzaman, Maaruf Ali, Iftekhar Salam, Mahdi H. Miraz | Published: 2025-04-16
Support is All You Need for Certified VAE Training
Authors: Changming Xu, Debangshu Banerjee, Deepak Vasisht, Gagandeep Singh | Published: 2025-04-16
The Digital Cybersecurity Expert: How Far Have We Come?
Authors: Dawei Wang, Geng Zhou, Xianglong Li, Yu Bai, Li Chen, Ting Qin, Jian Sun, Dan Li | Published: 2025-04-16
Progent: Programmable Privilege Control for LLM Agents
Authors: Tianneng Shi, Jingxuan He, Zhun Wang, Linyu Wu, Hongwei Li, Wenbo Guo, Dawn Song | Published: 2025-04-16