AIセキュリティポータルbot

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
2025.06.11 2025.06.13
Literature Database

Private Aggregation for Byzantine-Resilient Heterogeneous Federated Learning

Authors: Maximilian Egger, Rawad Bitar | Published: 2025-06-11
Privacy protection framework
Robustness Evaluation
Federated Learning
2025.06.11 2025.06.13
Literature Database

Evasion Attacks Against Bayesian Predictive Models

Authors: Pablo G. Arce, Roi Naveiro, David Ríos Insua | Published: 2025-06-11
Backdoor Attack
Bayesian Adversarial Learning
Adversarial Perturbation Techniques
2025.06.11 2025.06.13
Literature Database

Learning Obfuscations Of LLM Embedding Sequences: Stained Glass Transform

Authors: Jay Roberts, Kyle Mylonakis, Sidhartha Roy, Kaan Kale | Published: 2025-06-11
Privacy Enhancing Technology
Differential Privacy
情報理論的関係
2025.06.11 2025.06.13
Literature Database

LLMs Cannot Reliably Judge (Yet?): A Comprehensive Assessment on the Robustness of LLM-as-a-Judge

Authors: Songze Li, Chuokun Xu, Jiaying Wang, Xueluan Gong, Chen Chen, Jirui Zhang, Jun Wang, Kwok-Yan Lam, Shouling Ji | Published: 2025-06-11
Disabling Safety Mechanisms of LLM
Prompt Injection
Adversarial attack
2025.06.11 2025.06.13
Literature Database

Adversarial Surrogate Risk Bounds for Binary Classification

Authors: Natalie S. Frank | Published: 2025-06-11
Certified Robustness
Convergence Analysis
Function Boundary Pair Formation
2025.06.11 2025.06.13
Literature Database

Design Patterns for Securing LLM Agents against Prompt Injections

Authors: Luca Beurer-Kellner, Beat Buesser Ana-Maria Creţu, Edoardo Debenedetti, Daniel Dobos, Daniel Fabian, Marc Fischer, David Froelicher, Kathrin Grosse, Daniel Naeff, Ezinwanne Ozoani, Andrew Paverd, Florian Tramèr, Václav Volhejn | Published: 2025-06-10 | Updated: 2025-06-11
Indirect Prompt Injection
Prompt Injection
Defense Method
2025.06.10 2025.06.13
Literature Database

Your Agent Can Defend Itself against Backdoor Attacks

Authors: Li Changjiang, Liang Jiacheng, Cao Bochuan, Chen Jinghui, Wang Ting | Published: 2025-06-10 | Updated: 2025-06-11
Poisoning attack on RAG
Backdoor Attack Mitigation
Defense Method
2025.06.10 2025.06.13
Literature Database

Understanding the Error Sensitivity of Privacy-Aware Computing

Authors: Matías Mazzanti, Esteban Mocskos, Augusto Vega, Pradip Bose | Published: 2025-06-09
Error Correction Code
Privacy Protection Mechanism
Encryption Technology
2025.06.09 2025.06.11
Literature Database

TokenBreak: Bypassing Text Classification Models Through Token Manipulation

Authors: Kasimir Schulz, Kenneth Yeung, Kieran Evans | Published: 2025-06-09
Adversarial Attack Methods
Defense Method
2025.06.09 2025.06.11
Literature Database
Next page