Digital Forgetting in Large Language Models: A Survey of Unlearning Methods
Authors: Alberto Blanco-Justicia, Najeeb Jebreel, Benet Manzanares, David Sánchez, Josep Domingo-Ferrer, Guillem Collell, Kuan Eeik Tan | Published: 2024-04-02
プロンプトインジェクション
What is in Your Safe Data? Identifying Benign Data that Breaks Safety
Authors: Luxi He, Mengzhou Xia, Peter Henderson | Published: 2024-04-01 | Updated: 2024-08-20
To Err is Machine: Vulnerability Detection Challenges LLM Reasoning
Authors: Benjamin Steenhoek, Md Mahbubur Rahman, Monoshi Kumar Roy, Mirza Sanjida Alam, Hengbo Tong, Swarna Das, Earl T. Barr, Wei Le | Published: 2024-03-25 | Updated: 2025-01-07
Defending Against Indirect Prompt Injection Attacks With Spotlighting
Authors: Keegan Hines, Gary Lopez, Matthew Hall, Federico Zarfati, Yonatan Zunger, Emre Kiciman | Published: 2024-03-20
Leveraging Large Language Models to Detect npm Malicious Packages
Authors: Nusrat Zahan, Philipp Burckhardt, Mikola Lysenko, Feross Aboukhadijeh, Laurie Williams | Published: 2024-03-18 | Updated: 2025-01-06
Helpful or Harmful? Exploring the Efficacy of Large Language Models for Online Grooming Prevention
Authors: Ellie Prosser, Matthew Edwards | Published: 2024-03-14
AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting
Authors: Yu Wang, Xiaogeng Liu, Yu Li, Muhao Chen, Chaowei Xiao | Published: 2024-03-14
CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion
Authors: Qibing Ren, Chang Gao, Jing Shao, Junchi Yan, Xin Tan, Wai Lam, Lizhuang Ma | Published: 2024-03-12 | Updated: 2024-09-14
ACFIX: Guiding LLMs with Mined Common RBAC Practices for Context-Aware Repair of Access Control Vulnerabilities in Smart Contracts
Authors: Lyuye Zhang, Kaixuan Li, Kairan Sun, Daoyuan Wu, Ye Liu, Haoye Tian, Yang Liu | Published: 2024-03-11 | Updated: 2024-03-18
DP-TabICL: In-Context Learning with Differentially Private Tabular Data
Authors: Alycia N. Carey, Karuna Bhaila, Kennedy Edemacu, Xintao Wu | Published: 2024-03-08