Paper Library

Multi-turn Jailbreaking via Global Refinement and Active Fabrication

Hua Tang, Lingyong Yan, Yukun Zhao, Shuaiqiang Wang, Jizhou Huang, Dawei Yin

2025-06-22

red teaming

2506.17881v1

Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs

Shuang Ao, Yi Dong, Jinwei Hu, Sarvapali Ramchurn

2025-06-21

safety

2506.18931v1

SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification

Zhenglin Lai, Mengyao Liao, Dong Xu, Zebin Zhao, Zhihang Yuan, Chao Fan, Jianqiang Li, Bingzhe Wu

2025-06-20

safety

2506.17368v1

From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers

Jingtong Su, Julia Kempe, Karen Ullrich

2025-06-20

red teaming

2506.17052v1

MIST: Jailbreaking Black-box Large Language Models via Iterative Semantic Tuning

Muyang Zheng, Yuanzhi Yao, Changting Lin, Rui Wang, Meng Han

2025-06-20

red teaming

2506.16792v1

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models

Lei Jiang, Zixun Zhang, Zizhou Wang, Xiaobing Sun, Zhen Li, Liangli Zhen, Xiaohua Xu

2025-06-20

red teaming

2506.16760v1

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models

Biao Yi, Tiansheng Huang, Sishuo Chen, Tong Li, Zheli Liu, Zhixuan Chu, Yiming Li

2025-06-19

red teaming

2506.16447v1

Probing the Robustness of Large Language Models Safety to Latent Perturbations

Tianle Gu, Kexin Huang, Zongqi Wang, Yixu Wang, Jie Li, Yuanqi Yao, Yang Yao, Yujiu Yang, Yan Teng, Yingchun Wang

2025-06-19

red teaming

2506.16078v1

deepSURF: Detecting Memory Safety Vulnerabilities in Rust Through Fuzzing LLM-Augmented Harnesses

Georgios Androutsopoulos, Antonio Bianchi

2025-06-18

safety

2506.15648v1

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning

Gabrel J. Perin, Runjin Chen, Xuxi Chen, Nina S. T. Hirata, Zhangyang Wang, Junyuan Hong

2025-06-18

safety

2506.15606v1

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem

Yanxu Mao, Tiehan Cui, Peipei Liu, Datao You, Hongsong Zhu

2025-06-18

red teaming safety

2506.15170v1

Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts

Kartik Sharma, Yiqiao Jin, Vineeth Rakesh, Yingtong Dou, Menghai Pan, Mahashweta Das, Srijan Kumar

2025-06-18

red teaming

2506.15751v1

LLM Jailbreak Oracle

Shuyi Lin, Anshuman Suri, Alina Oprea, Cheng Tan

2025-06-17

red teaming

2506.17299v1

Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations

Abhilekh Borah, Chhavi Sharma, Danush Khanna, Utkarsh Bhatt, Gurpreet Singh, Hasnat Md Abdullah, Raghav Kaushik Ravi, Vinija Jain, Jyoti Patel, Shubham Singh, Vasu Sharma, Arpita Vats, Rahul Raja, Aman Chadha, Amitava Das

2025-06-16

red teaming

2506.13901v1

Safe-Child-LLM: A Developmental Benchmark for Evaluating LLM Safety in Child-LLM Interactions

Junfeng Jiao, Saleh Afroogh, Kevin Chen, Abhejay Murali, David Atkinson, Amit Dhurandhar

2025-06-16

red teaming safety

2506.13510v2

Safe-Child-LLM: A Developmental Benchmark for Evaluating LLM Safety in Child-AI Interactions

Junfeng Jiao, Saleh Afroogh, Kevin Chen, Abhejay Murali, David Atkinson, Amit Dhurandhar

2025-06-16

red teaming safety

2506.13510v1

Mitigating Safety Fallback in Editing-based Backdoor Injection on LLMs

Houcheng Jiang, Zetong Zhao, Junfeng Fang, Haokai Ma, Ruipeng Wang, Yang Deng, Xiang Wang, Xiangnan He

2025-06-16

safety

2506.13285v1

June 23 - June 29, 2025

Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation

A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures

PrivacyXray: Detecting Privacy Breaches in LLMs through Semantic Consistency and Probability Certainty

MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language Models

Command-V: Pasting LLM Behaviors via Activation Profiles

Security Assessment of DeepSeek and GPT Series Models against Jailbreak Attacks

NSFW-Classifier Guided Prompt Sanitization for Safe Text-to-Image Generation

June 16 - June 22, 2025

Multi-turn Jailbreaking via Global Refinement and Active Fabrication

Safe Pruning LoRA: Robust Distance-Guided Pruning for Safety Alignment in Adaptation of LLMs

SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification

From Concepts to Components: Concept-Agnostic Attention Module Discovery in Transformers

MIST: Jailbreaking Black-box Large Language Models via Iterative Semantic Tuning

Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models

Probing the Robustness of Large Language Models Safety to Latent Perturbations

deepSURF: Detecting Memory Safety Vulnerabilities in Rust Through Fuzzing LLM-Augmented Harnesses

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning

From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem

Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts

LLM Jailbreak Oracle

Alignment Quality Index (AQI) : Beyond Refusals: AQI as an Intrinsic Alignment Diagnostic via Latent Geometry, Cluster Divergence, and Layer wise Pooled Representations

Safe-Child-LLM: A Developmental Benchmark for Evaluating LLM Safety in Child-LLM Interactions

Safe-Child-LLM: A Developmental Benchmark for Evaluating LLM Safety in Child-AI Interactions

Mitigating Safety Fallback in Editing-based Backdoor Injection on LLMs