AIセキュリティポータルbot

SoK: Taxonomy and Evaluation of Prompt Security in Large Language Models

Authors: Hanbin Hong, Shuya Feng, Nima Naderloui, Shenao Yan, Jingyu Zhang, Biying Liu, Ali Arastehfard, Heqing Huang, Yuan Hong | Published: 2025-10-17 | Updated: 2025-10-21
LLM Security
シナリオベースの悪用
Large Language Model
2025.10.17 2025.10.23
Literature Database

OCR-APT: Reconstructing APT Stories from Audit Logs using Subgraph Anomaly Detection and LLMs

Authors: Ahmed Aly, Essam Mansour, Amr Youssef | Published: 2025-10-16 | Updated: 2025-10-20
APT攻撃調査
GNNベースの異常検知
Anomaly Detection Method
2025.10.16 2025.10.22
Literature Database

A Hard-Label Black-Box Evasion Attack against ML-based Malicious Traffic Detection Systems

Authors: Zixuan Liu, Yi Zhao, Zhuotao Liu, Qi Li, Chuanpu Fu, Guangmeng Zhou, Ke Xu | Published: 2025-10-16
Modification of Network Traffic
Botnet Traffic
Model Extraction Attack
2025.10.16 2025.10.18
Literature Database

Secure Sparse Matrix Multiplications and their Applications to Privacy-Preserving Machine Learning

Authors: Marc Damie, Florian Hahn, Andreas Peter, Jan Ramon | Published: 2025-10-16
Data Protection
Privacy-Preserving Machine Learning
Differential Privacy
2025.10.16 2025.10.18
Literature Database

LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?

Authors: Bin Liu, Yanjie Zhao, Guoai Xu, Haoyu Wang | Published: 2025-10-16
Indirect Prompt Injection
エージェント設計
Security Analysis
2025.10.16 2025.10.18
Literature Database

Lexo: Eliminating Stealthy Supply-Chain Attacks via LLM-Assisted Program Regeneration

Authors: Evangelos Lamprou, Julian Dai, Grigoris Ntousakis, Martin C. Rinard, Nikos Vasilakis | Published: 2025-10-16
Security Analysis
Program Verification
Prompt leaking
2025.10.16 2025.10.18
Literature Database

Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers

Authors: Andrew Zhao, Reshmi Ghosh, Vitor Carvalho, Emily Lawton, Keegan Hines, Gao Huang, Jack W. Stokes | Published: 2025-10-16
Prompt Injection
Prompt leaking
Large Language Model
2025.10.16 2025.10.18
Literature Database

Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies

Authors: Mason Nakamura, Abhinav Kumar, Saaduddin Mahmud, Sahar Abdelnabi, Shlomo Zilberstein, Eugene Bagdasarian | Published: 2025-10-16
エージェント設計
Large Language Model
通信プロトコル
2025.10.16 2025.10.18
Literature Database

RHINO: Guided Reasoning for Mapping Network Logs to Adversarial Tactics and Techniques with Large Language Models

Authors: Fanchao Meng, Jiaping Gui, Yunbo Li, Yue Wu | Published: 2025-10-16
Network Traffic Analysis
Backdoor Detection
Evaluation Method
2025.10.16 2025.10.18
Literature Database

In-Browser LLM-Guided Fuzzing for Real-Time Prompt Injection Testing in Agentic AI Browsers

Authors: Avihay Cohen | Published: 2025-10-15
Indirect Prompt Injection
Large Language Model
自動生成フレームワーク
2025.10.15 2025.10.17
Literature Database
Next page