AIセキュリティポータルbot

Protection against Source Inference Attacks in Federated Learning

Authors: Andreas Athanasiou, Kangsoo Jung, Catuscia Palamidessi | Published: 2026-03-02
Secure Aggregation
Trigger Detection
Poisoning
2026.03.02 2026.03.04
Literature Database

Real Money, Fake Models: Deceptive Model Claims in Shadow APIs

Authors: Yage Zhang, Yukun Jiang, Zeyuan Chen, Michael Backes, Xinyue Shen, Yang Zhang | Published: 2026-03-02
LLM Performance Evaluation
Data Privacy Management
2026.03.02 2026.03.04
Literature Database

Co-Evolutionary Multi-Modal Alignment via Structured Adversarial Evolution

Authors: Guoxin Shi, Haoyu Wang, Zaihui Yang, Yuxing Wang, Yongzhe Chang | Published: 2026-03-02
Alignment
安全性評価
機械学習応用
2026.03.02 2026.03.04
Literature Database

DualSentinel: A Lightweight Framework for Detecting Targeted Attacks in Black-box LLM via Dual Entropy Lull Pattern

Authors: Xiaoyi Pang, Xuanyi Hao, Pengyu Liu, Qi Luo, Song Guo, Zhibo Wang | Published: 2026-03-02
LLM Performance Evaluation
Indirect Prompt Injection
Prompt Injection
2026.03.02 2026.03.04
Literature Database

From Secure Agentic AI to Secure Agentic Web: Challenges, Threats, and Future Directions

Authors: Zhihang Deng, Jiaping Gui, Weinan Zhang | Published: 2026-03-02
Indirect Prompt Injection
安全性評価
Threat Model
2026.03.02 2026.03.04
Literature Database

Towards Privacy-Preserving LLM Inference via Collaborative Obfuscation (Technical Report)

Authors: Yu Lin, Qizhi Zhang, Wenqiang Ruan, Daode Zhang, Jue Hong, Ye Wu, Hanning Xia, Yunlong Mao, Sheng Zhong | Published: 2026-03-02
Disabling Safety Mechanisms of LLM
LLM Performance Evaluation
Differential Privacy
2026.03.02 2026.03.04
Literature Database

Inference-Time Safety For Code LLMs Via Retrieval-Augmented Revision

Authors: Manisha Mukherjee, Vincent J. Hellendoorn | Published: 2026-03-02
Indirect Prompt Injection
セキュリティに関連する知識を活用した手法
Prompt leaking
2026.03.02 2026.03.04
Literature Database

LLM Novice Uplift on Dual-Use, In Silico Biology Tasks

Authors: Chen Bo Calvin Zhang, Christina Q. Knight, Nicholas Kruus, Jason Hausenloy, Pedro Medeiros, Nathaniel Li, Aiden Kim, Yury Orlovskiy, Coleman Breen, Bryce Cai, Jasper Götting, Andrew Bo Liu, Samira Nedungadi, Paula Rodriguez, Yannis Yiming He, Mohamed Shaaban, Zifan Wang, Seth Donoughe, Julian Michael | Published: 2026-02-26
LLM Performance Evaluation
Model evaluation methods
Educational Data Mining
2026.02.26 2026.02.28
Literature Database

A Decision-Theoretic Formalisation of Steganography With Applications to LLM Monitoring

Authors: Usman Anwar, Julianna Piskorz, David D. Baek, David Africa, Jim Weatherall, Max Tegmark, Christian Schroeder de Witt, Mihaela van der Schaar, David Krueger | Published: 2026-02-26
Watermarking
Data Management System
Model evaluation methods
2026.02.26 2026.02.28
Literature Database

Assessing Deanonymization Risks with Stylometry-Assisted LLM Agent

Authors: Boyang Zhang, Yang Zhang | Published: 2026-02-26
Disabling Safety Mechanisms of LLM
Data Privacy Assessment
Prompt leaking
2026.02.26 2026.02.28
Literature Database
Next page