Philipp Zimmermann
← Back to Newsletter

Paper Library

Collection of AI Security research papers

Showing 947 papers total

December 29 - January 04, 2026

6 papers

Language Model Agents Under Attack: A Cross Model-Benchmark of Profit-Seeking Behaviors in Customer Service

Jingyu Zhang
2025-12-30
red teaming
2512.24415v1

The Silicon Psyche: Anthropomorphic Vulnerabilities in Large Language Models

Giuseppe Canale, Kashyap Thimmaraju
2025-12-30
red teaming
2601.00867v1

Multilingual Hidden Prompt Injection Attacks on LLM-Based Academic Reviewing

Panagiotis Theocharopoulos, Ajinkya Kulkarni, Mathew Magimai. -Doss
2025-12-29
red teaming
2512.23684v1

Toward Trustworthy Agentic AI: A Multimodal Framework for Preventing Prompt Injection Attacks

Toqeer Ali Syed, Mishal Ateeq Almutairi, Mahmoud Abdel Moaty
2025-12-29
2512.23557v1

Multi-Agent Framework for Threat Mitigation and Resilience in AI-Based Systems

Armstrong Foundjem, Lionel Nganyewou Tidjon, Leuson Da Silva, Foutse Khomh
2025-12-29
red teaming
2512.23132v1

It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents

Karolina Korgul, Yushi Yang, Arkadiusz Drohomirecki, Piotr Błaszczyk, Will Howard, Lukas Aichberger, Chris Russell, Philip H. S. Torr, Adam Mahdi, Adel Bibi
2025-12-29
red teaming
2512.23128v1

December 22 - December 28, 2025

7 papers

Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization

Kerem Zaman, Shashank Srivastava
2025-12-28
2512.23032v1

Look Closer! An Adversarial Parametric Editing Framework for Hallucination Mitigation in VLMs

Jiayu Hu, Beibei Li, Jiangwei Xia, Yanjun Qin, Bing Ji, Zhongshi He
2025-12-26
2512.21999v1

AegisAgent: An Autonomous Defense Agent Against Prompt Injection Attacks in LLM-HARs

Yihan Wang, Huanqi Yang, Shantanu Pal, Weitao Xu
2025-12-24
red teaming
2512.20986v1

ChatGPT: Excellent Paper! Accept It. Editor: Imposter Found! Review Rejected

Kanchon Gharami, Sanjiv Kumar Sarkar, Yongxin Liu, Shafika Showkat Moni
2025-12-23
red teaming
2512.20405v2

AprielGuard

Jaykumar Kasundra, Anjaneya Praharaj, Sourabh Surana, Lakshmi Sirisha Chodisetty, Sourav Sharma, Abhigya Verma, Abhishek Bhardwaj, Debasish Kanhar, Aakash Bhagat, Khalil Slimi, Seganrasan Subramanian, Sathwik Tejaswi Madhusudhan, Ranga Prasad Chenna, Srinivas Sunkara
2025-12-23
red teaming
2512.20293v2

PromptScreen: Efficient Jailbreak Mitigation Using Semantic Linear Classification in a Multi-Staged Pipeline

Akshaj Prashanth Rao, Advait Singh, Saumya Kumaar Saksena, Dhruv Kumar
2025-12-22
red teaming
2512.19011v2

Efficient Jailbreak Mitigation Using Semantic Linear Classification in a Multi-Staged Pipeline

Akshaj Prashanth Rao, Advait Singh, Saumya Kumaar Saksena, Dhruv Kumar
2025-12-22
2512.19011v1

December 15 - December 21, 2025

7 papers

Rubric-Conditioned LLM Grading: Alignment, Uncertainty, and Robustness

Haotian Deng, Chris Farber, Jiyoon Lee, David Tang
2025-12-21
red teaming
2601.08843v1

Beyond the Benchmark: Innovative Defenses Against Prompt Injection Attacks

Safwan Shaheer, G. M. Refatul Islam, Mohammad Rafid Hamid, Tahsin Zaman Jilan
2025-12-18
red teaming
2512.16307v1

MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval

Saksham Sahai Srivastava, Haoyu He
2025-12-18
red teaming
2512.16962v1

Quantifying Return on Security Controls in LLM Systems

Richard Helder Moulton, Austin O'Brien, John D. Hastings
2025-12-17
red teaming
2512.15081v1

Trust in LLM-controlled Robotics: a Survey of Security Threats, Defenses and Challenges

Xinyu Huang, Shyam Karthick V B, Taozhao Chen, Mitch Bryson, Thomas Chaffey, Huaming Chen, Kim-Kwang Raymond Choo, Ian R. Manchester
2025-12-17
red teaming
2601.02377v1

Penetration Testing of Agentic AI: A Comparative Security Analysis Across Models and Frameworks

Viet K. Nguyen, Mohammad I. Husain
2025-12-16
red teaming
2512.14860v1

Cisco Integrated AI Security and Safety Framework Report

Amy Chang, Tiffany Saade, Sanket Mendapara, Adam Swanda, Ankit Garg
2025-12-15
red teaming
2512.12921v1

December 08 - December 14, 2025

4 papers

ceLLMate: Sandboxing Browser AI Agents

Luoxi Meng, Henry Feng, Ilia Shumailov, Earlence Fernandes
2025-12-14
2512.12594v1

Detecting Prompt Injection Attacks Against Application Using Classifiers

Safwan Shaheer, G. M. Refatul Islam, Mohammad Rafid Hamid, Md. Abrar Faiaz Khan, Md. Omar Faruk, Yaseen Nur
2025-12-14
red teaming
2512.12583v1

Challenges of Evaluating LLM Safety for User Welfare

Manon Kempermann, Sai Suresh Macharla Vasu, Mahalakshmi Raveenthiran, Theo Farrell, Ingmar Weber
2025-12-11
safety
2512.10687v1

When Reject Turns into Accept: Quantifying the Vulnerability of LLM-Based Scientific Reviewers to Indirect Prompt Injection

Devanshu Sahoo, Manish Prasad, Vasudev Majhi, Jahnvi Singh, Vinay Chamola, Yash Sinha, Murari Mandal, Dhruv Kumar
2025-12-11
red teaming
2512.10449v3