Paper Library

Keep Calm and Avoid Harmful Content: Concept Alignment and Latent Manipulation Towards Safer Answers

Ruben Belo, Marta Guimaraes, Claudia Soares

2025-10-14

2510.12672v2

Keep Calm and Avoid Harmful Content: Concept Alignment and Latent Manipulation Towards Safer Answers

Ruben Belo, Claudia Soares, Marta Guimaraes

2025-10-14

2510.12672v1

Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection

Olga E. Sorokoletova, Francesco Giarrusso, Vincenzo Suriani, Daniele Nardi

2025-10-14

red teaming

2510.13893v1

PromptLocate: Localizing Prompt Injection Attacks

Yuqi Jia, Yupei Liu, Zedian Shao, Jinyuan Jia, Neil Gong

2025-10-14

red teaming

2510.12252v2

MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents

Dongsen Zhang, Zekun Li, Xu Luo, Xuannan Liu, Peipei Li, Wenjun Xu

2025-10-14

red teaming

2510.15994v1

SafeMT: Multi-turn Safety for Multimodal Language Models

Han Zhu, Juntao Dai, Jiaming Ji, Haoran Li, Chengkun Cai, Pengcheng Wen, Chi-Min Chan, Boyuan Chen, Yaodong Yang, Sirui Han, Yike Guo

2025-10-14

red teaming

2510.12133v1

Deep Research Brings Deeper Harm

Shuo Chen, Zonggen Li, Zhen Han, Bailan He, Tong Liu, Haokun Chen, Georg Groh, Philip Torr, Volker Tresp, Jindong Gu

2025-10-13

red teaming

2510.11851v2

Deep Research Brings Deeper Harm

Shuo Chen, Zonggen Li, Zhen Han, Bailan He, Tong Liu, Haokun Chen, Georg Groh, Philip Torr, Volker Tresp, Jindong Gu

2025-10-13

red teaming

2510.11851v1

Countermind: A Multi-Layered Security Architecture for Large Language Models

Dominik Schwarz

2025-10-13

2510.11837v1

Don't Walk the Line: Boundary Guidance for Filtered Generation

Sarah Ball, Andreas Haupt

2025-10-13

2510.11834v1

Bag of Tricks for Subverting Reasoning-based Safety Guardrails

Shuo Chen, Zhen Han, Haokun Chen, Bailan He, Shengyun Si, Jingpei Wu, Philip Torr, Volker Tresp, Jindong Gu

2025-10-13

red teaming

2510.11570v1

Beyond the Crowd: LLM-Augmented Community Notes for Governing Health Misinformation

Jiaying Wu, Zihang Fu, Haonan Wang, Fanxiao Li, Min-Yen Kan

2025-10-13

governance

2510.11423v1

Attacks by Content: Automated Fact-checking is an AI Security Issue

Michael Schlichtkrull

2025-10-13

2510.11238v1

TypePilot: Leveraging the Scala Type System for Secure LLM-generated Code

Alexander Sternfeld, Andrei Kucharavy, Ljiljana Dolamic

2025-10-13

2510.11151v1

Demystifying Numerosity in Diffusion Models -- Limitations and Remedies

Yaqi Zhao, Xiaochen Wang, Li Dong, Wentao Zhang, Yuhui Yuan

2025-10-13

2510.11117v1

SceneTextStylizer: A Training-Free Scene Text Style Transfer Framework with Diffusion Model

Honghui Yuan, Keiji Yanai

2025-10-13

2510.10910v1

October 13 - October 19, 2025

Keep Calm and Avoid Harmful Content: Concept Alignment and Latent Manipulation Towards Safer Answers

Keep Calm and Avoid Harmful Content: Concept Alignment and Latent Manipulation Towards Safer Answers

Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection

PromptLocate: Localizing Prompt Injection Attacks

MCP Security Bench (MSB): Benchmarking Attacks Against Model Context Protocol in LLM Agents

SafeMT: Multi-turn Safety for Multimodal Language Models

Deep Research Brings Deeper Harm

Deep Research Brings Deeper Harm

Countermind: A Multi-Layered Security Architecture for Large Language Models

Don't Walk the Line: Boundary Guidance for Filtered Generation

Bag of Tricks for Subverting Reasoning-based Safety Guardrails

Beyond the Crowd: LLM-Augmented Community Notes for Governing Health Misinformation

Attacks by Content: Automated Fact-checking is an AI Security Issue

TypePilot: Leveraging the Scala Type System for Secure LLM-generated Code

Demystifying Numerosity in Diffusion Models -- Limitations and Remedies

SceneTextStylizer: A Training-Free Scene Text Style Transfer Framework with Diffusion Model

October 06 - October 12, 2025

ArtPerception: ASCII Art-based Jailbreak on LLMs with Recognition Pre-test

MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation

MemPromptTSS: Persistent Prompt Memory for Iterative Multi-Granularity Time Series State Segmentation

Learning Bug Context for PyTorch-to-JAX Translation with LLMs

Text Prompt Injection of Vision Language Models

A Comprehensive Evaluation of Multilingual Chain-of-Thought Reasoning: Performance, Consistency, and Faithfulness Across Languages

Multimodal Policy Internalization for Conversational Agents

Getting Your Indices in a Row: Full-Text Search for LLM Training Data for Real World