Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs
Authors: Man Hu, Xinyi Wu, Zuofeng Suo, Jinbo Feng, Linghui Meng, Yanhao Jia, Anh Tuan Luu, Shuai Zhao | Published: 2025-10-09
プロンプトリーキング
Fine-Tuning Jailbreaks under Highly Constrained Black-Box Settings: A Three-Pronged Approach
Authors: Xiangfang Li, Yu Wang, Bo Li | Published: 2025-10-01 | Updated: 2025-10-09
MaskSQL: Safeguarding Privacy for LLM-Based Text-to-SQL via Abstraction
Authors: Sepideh Abedini, Shubhankar Mohapatra, D. B. Emerson, Masoumeh Shafieinejad, Jesse C. Cresswell, Xi He | Published: 2025-09-27 | Updated: 2025-09-30
Enterprise AI Must Enforce Participant-Aware Access Control
Authors: Shashank Shreedhar Bhatt, Tanmay Rajore, Khushboo Aggarwal, Ganesh Ananthanarayanan, Ranveer Chandra, Nishanth Chandran, Suyash Choudhury, Divya Gupta, Emre Kiciman, Sumit Kumar Pandey, Srinath Setty, Rahul Sharma, Teijia Zhao | Published: 2025-09-18
Yet Another Watermark for Large Language Models
Authors: Siyuan Bao, Ying Shi, Zhiguang Yang, Hanzhou Wu, Xinpeng Zhang | Published: 2025-09-16
PromptCOS: Towards System Prompt Copyright Auditing for LLMs via Content-level Output Similarity
Authors: Yuchen Yang, Yiming Li, Hongwei Yao, Enhao Huang, Shuo Shao, Bingrun Yang, Zhibo Wang, Dacheng Tao, Zhan Qin | Published: 2025-09-03
The Double-edged Sword of LLM-based Data Reconstruction: Understanding and Mitigating Contextual Vulnerability in Word-level Differential Privacy Text Sanitization
Authors: Stephen Meisenbacher, Alexandra Klymenko, Andreea-Elena Bodea, Florian Matthes | Published: 2025-08-26
Membership Inference Attacks on LLM-based Recommender Systems
Authors: Jiajie He, Yuechun Gu, Min-Chun Chen, Keke Chen | Published: 2025-08-26
MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols
Authors: Yixuan Yang, Daoyuan Wu, Yufan Chen | Published: 2025-08-17 | Updated: 2025-10-09
VFLAIR-LLM: A Comprehensive Framework and Benchmark for Split Learning of LLMs
Authors: Zixuan Gu, Qiufeng Fan, Long Sun, Yang Liu, Xiaojun Ye | Published: 2025-08-05