Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
Authors: Yuanpu Cao, Bochuan Cao, Jinghui Chen | Published: 2023-11-15 | Updated: 2024-06-09
文献データベース
HAL 9000: Skynet’s Risk Manager
Authors: Tadeu Freitas, Mário Neto, Inês Dutra, João Soares, Manuel Correia, Rolando Martins | Published: 2023-11-15
Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment
Authors: Haoran Wang, Kai Shu | Published: 2023-11-15 | Updated: 2024-08-15
Are Normalizing Flows the Key to Unlocking the Exponential Mechanism?
Authors: Robert A. Bridges, Vandy J. Tombs, Christopher B. Stanley | Published: 2023-11-15 | Updated: 2024-06-11
Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts
Authors: Yuanwei Wu, Xiang Li, Yixin Liu, Pan Zhou, Lichao Sun | Published: 2023-11-15 | Updated: 2024-01-20
A Robust Semantics-based Watermark for Large Language Model against Paraphrasing
Authors: Jie Ren, Han Xu, Yiding Liu, Yingqian Cui, Shuaiqiang Wang, Dawei Yin, Jiliang Tang | Published: 2023-11-15 | Updated: 2024-04-01
KnowSafe: Combined Knowledge and Data Driven Hazard Mitigation in Artificial Pancreas Systems
Authors: Xugui Zhou, Maxfield Kouzel, Chloe Smith, Homa Alemzadeh | Published: 2023-11-13
Adversarial Purification for Data-Driven Power System Event Classifiers with Diffusion Models
Authors: Yuanbin Cheng, Koji Yamashita, Jim Follum, Nanpeng Yu | Published: 2023-11-13
Seeing is Believing: A Federated Learning Based Prototype to Detect Wireless Injection Attacks
Authors: Aadil Hussain, Nitheesh Gundapu, Sarang Drugkar, Suraj Kiran, J. Harshan, Ranjitha Prasad | Published: 2023-11-11
Does Differential Privacy Prevent Backdoor Attacks in Practice?
Authors: Fereshteh Razmi, Jian Lou, Li Xiong | Published: 2023-11-10