Paper Library

Prompt Injection Evaluations: Refusal Boundary Instability and Artifact-Dependent Compliance in GPT-4-Series Models

Thomas Heverin

2026-01-25

red teaming

2601.17911v1

Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents

Narek Maloyan, Dmitry Namiot

2026-01-24

red teaming

2601.17549v1

Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems

Narek Maloyan, Dmitry Namiot

2026-01-24

red teaming

2601.17548v1

Physical Prompt Injection Attacks on Large Vision-Language Models

Chen Ling, Kai Hu, Hangcheng Liu, Xingshuo Han, Tianwei Zhang, Changhai Ou

2026-01-24

red teaming

2601.17383v1

SafeThinker: Reasoning about Risk to Deepen Safety Beyond Shallow Alignment

Xianya Fang, Xianying Luo, Yadong Wang, Xiang Chen, Yu Tian, Zequn Sun, Rui Liu, Jun Fang, Naiqiang Tan, Yuanning Cui, Sheng-Jun Huang

2026-01-23

red teaming

2601.16506v1

Persona Jailbreaking in Large Language Models

Jivnesh Sandhan, Fei Cheng, Tushar Sandhan, Yugo Murawaki

2026-01-23

red teaming

2601.16466v1

Machine-Assisted Grading of Nationwide School-Leaving Essay Exams with LLMs and Statistical NLP

Andres Karjus, Kais Allkivi, Silvia Maine, Katarin Leppik, Krister Kruusmaa, Merilin Aruvee

2026-01-22

2601.16314v1

Attributing and Exploiting Safety Vectors through Global Optimization in Large Language Models

Fengheng Chu, Jiahao Chen, Yuhong Wang, Jun Wang, Zhihui Fu, Shouling Ji, Songze Li

2026-01-22

red teaming

2601.15801v1

Improving Methodologies for LLM Evaluations Across Global Languages

Akriti Vij, Benjamin Chua, Darshini Ramiah, En Qi Ng, Mahran Morsidi, Naga Nikshith Gangarapu, Sharmini Johnson, Vanessa Wilfred, Vikneswaran Kumaran, Wan Sie Lee, Wenzhuo Yang, Yongsen Zheng, Bill Black, Boming Xia, Frank Sun, Hao Zhang, Qinghua Lu, Suyu Ma, Yue Liu, Chi-kiu Lo, Fatemeh Azadi, Isar Nejadgholi, Sowmya Vajjala, Agnes Delaborde, Nicolas Rolin, Tom Seimandi, Akiko Murakami, Haruto Ishi, Satoshi Sekine, Takayuki Semitsu, Tasuku Sasaki, Angela Kinuthia, Jean Wangari, Michael Michie, Stephanie Kasaon, Hankyul Baek, Jaewon Noh, Kihyuk Nam, Sang Seo, Sungpil Shin, Taewhi Lee, Yongsu Kim, Daisy Newbold-Harrop, Jessica Wang, Mahmoud Ghanem, Vy Hong

2026-01-22

2601.15706v1

Beyond Visual Safety: Jailbreaking Multimodal Large Language Models for Harmful Image Generation via Semantic-Agnostic Inputs

Mingyu Yu, Lana Liu, Zhehao Zhao, Wei Wang, Sujuan Qin

2026-01-22

red teaming

2601.15698v1

Securing LLM-as-a-Service for Small Businesses: An Industry Case Study of a Distributed Chatbot Deployment Platform

Jiazhu Xie, Bowen Li, Heyu Fu, Chong Gao, Ziqi Xu, Fengling Han

2026-01-21

2601.15528v1

From Biased Chatbots to Biased Agents: Examining Role Assignment Effects on LLM Agent Robustness

Linbo Cao, Lihao Sun, Yang Yue

2026-01-21

2602.12285v1

LLM Security and Safety: Insights from Homotopy-Inspired Prompt Obfuscation

Luis Lazo, Hamed Jelodar, Roozbeh Razavi-Far

2026-01-20

safety

2601.14528v1

RECAP: A Resource-Efficient Method for Adversarial Prompting in Large Language Models

Rishit Chugh

2026-01-20

red teaming

2601.15331v1

January 26 - February 01, 2026

ICON: Intent-Context Coupling for Efficient Multi-Turn Jailbreak Attack

RvB: Automating AI System Hardening via Iterative Red-Blue Games

LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment

SHIELD: An Auto-Healing Agentic Defense Framework for LLM Resource Exhaustion Attacks

Proactive Hardening of LLM Defenses with HASTE

Malicious Repurposing of Open Science Artefacts by Using Large Language Models

TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment

Beyond Retention: Orchestrating Structural Safety and Plasticity in Continual Learning for LLMs

From Transcripts to AI Agents: Knowledge Extraction, RAG Integration, and Robust Evaluation of Conversational AI Assistants

Comparison requires valid measurement: Rethinking attack success rate comparisons in AI red teaming

January 19 - January 25, 2026

Prompt Injection Evaluations: Refusal Boundary Instability and Artifact-Dependent Compliance in GPT-4-Series Models

Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents

Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems

Physical Prompt Injection Attacks on Large Vision-Language Models

SafeThinker: Reasoning about Risk to Deepen Safety Beyond Shallow Alignment

Persona Jailbreaking in Large Language Models

Machine-Assisted Grading of Nationwide School-Leaving Essay Exams with LLMs and Statistical NLP

Attributing and Exploiting Safety Vectors through Global Optimization in Large Language Models

Improving Methodologies for LLM Evaluations Across Global Languages

Beyond Visual Safety: Jailbreaking Multimodal Large Language Models for Harmful Image Generation via Semantic-Agnostic Inputs

Securing LLM-as-a-Service for Small Businesses: An Industry Case Study of a Distributed Chatbot Deployment Platform

From Biased Chatbots to Biased Agents: Examining Role Assignment Effects on LLM Agent Robustness

LLM Security and Safety: Insights from Homotopy-Inspired Prompt Obfuscation

RECAP: A Resource-Efficient Method for Adversarial Prompting in Large Language Models