Prompt Injection

Breaking the Boundaries of Long-Context LLM Inference: Adaptive KV Management on a Single Commodity GPU

Authors: He Sun, Li Li, Mingjun Xiao, Chengzhong Xu | Published: 2025-06-25
Prompt Injection
Memory Management Method
Evaluation Method

FuncVul: An Effective Function Level Vulnerability Detection Model using LLM and Code Chunk

Authors: Sajal Halder, Muhammad Ejaz Ahmed, Seyit Camtepe | Published: 2025-06-24
Prompt Injection
Large Language Model
Vulnerability Research

Security Assessment of DeepSeek and GPT Series Models against Jailbreak Attacks

Authors: Xiaodong Wu, Xiangman Li, Jianbing Ni | Published: 2025-06-23
Prompt Injection
Model Architecture
Large Language Model

Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases

Authors: Yubeen Bae, Minchan Kim, Jaejin Lee, Sangbum Kim, Jaehyung Kim, Yejin Choi, Niloofar Mireshghallah | Published: 2025-06-19 | Updated: 2025-07-01
Privacy Protection
Prompt Injection
Large Language Model

Evaluating Large Language Models for Phishing Detection, Self-Consistency, Faithfulness, and Explainability

Authors: Shova Kuikel, Aritran Piplai, Palvi Aggarwal | Published: 2025-06-16
Alignment
Prompt Injection
Large Language Model

Weakest Link in the Chain: Security Vulnerabilities in Advanced Reasoning Models

Authors: Arjun Krishna, Aaditya Rastogi, Erick Galinkin | Published: 2025-06-16
Prompt Injection
Large Language Model
Adversarial Attack Methods

SoK: Evaluating Jailbreak Guardrails for Large Language Models

Authors: Xunguang Wang, Zhenlan Ji, Wenxuan Wang, Zongjie Li, Daoyuan Wu, Shuai Wang | Published: 2025-06-12
Prompt Injection
Trade-Off Between Safety And Usability
脱獄攻撃手法

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks

Authors: Kaiyuan Zhang, Siyuan Cheng, Hanxi Guo, Yuetian Chen, Zian Su, Shengwei An, Yuntao Du, Charles Fleming, Ashish Kundu, Xiangyu Zhang, Ninghui Li | Published: 2025-06-12
Privacy Protection Method
Prompt Injection
Prompt leaking

ELFuzz: Efficient Input Generation via LLM-driven Synthesis Over Fuzzer Space

Authors: Chuyang Chen, Brendan Dolan-Gavitt, Zhiqiang Lin | Published: 2025-06-12
Fuzzing
Prompt Injection
効率的入力生成

LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge

Authors: Sahar Abdelnabi, Aideen Fay, Ahmed Salem, Egor Zverev, Kai-Chieh Liao, Chi-Huang Liu, Chun-Chih Kuo, Jannis Weigend, Danyael Manlangit, Alex Apostolov, Haris Umair, João Donato, Masayuki Kawakita, Athar Mahboob, Tran Huu Bach, Tsun-Han Chiang, Myeongjin Cho, Hajin Choi, Byeonghyeon Kim, Hyeonjin Lee, Benjamin Pannell, Conor McCauley, Mark Russinovich, Andrew Paverd, Giovanni Cherubin | Published: 2025-06-11
Indirect Prompt Injection
Prompt Injection
Defense Method