Paper Library

ENJ: Optimizing Noise with Genetic Algorithms to Jailbreak LSMs

Yibo Zhang, Liang Lin

2025-09-14

2509.11128v1

Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding

Seongho Joo, Hyukhun Koh, Kyomin Jung

2025-09-13

red teaming

2509.10931v1

Prompt Injection Attacks on LLM Generated Reviews of Scientific Publications

Janis Keuper

2025-09-12

red teaming

2509.10248v3

Realism Control One-step Diffusion for Real-World Image Super-Resolution

Zongliang Wu, Siming Zheng, Peng-Tao Jiang, Xin Yuan

2025-09-12

2509.10122v2

When Your Reviewer is an LLM: Biases, Divergence, and Prompt Injection Risks in Peer Review

Changjia Zhu, Junjie Xiong, Renkai Ma, Zhicong Lu, Yao Liu, Lingyao Li

2025-09-12

red teaming

2509.09912v1

Steering MoE LLMs via Expert (De)Activation

Mohsen Fayyaz, Ali Modarressi, Hanieh Deilamsalehy, Franck Dernoncourt, Ryan Rossi, Trung Bui, Hinrich Schütze, Nanyun Peng

2025-09-11

red teaming

2509.09660v1

Improving LLM Safety and Helpfulness using SFT and DPO: A Study on OPT-350M

Piyush Pant

2025-09-10

safety

2509.09055v1

PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability

Tung Vu, Lam Nguyen, Quynh Dao

2025-09-10

safety

2509.08910v1

X-Teaming Evolutionary M2S: Automated Discovery of Multi-turn to Single-turn Jailbreak Templates

Hyunjun Kim, Junwoo Ha, Sangyoon Yu, Haon Park

2025-09-10

red teaming

2509.08729v1

Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations

Ron F. Del Rosario, Klaudia Krawiecka, Christian Schroeder de Witt

2025-09-10

2509.08646v1

ImportSnare: Directed "Code Manual" Hijacking in Retrieval-Augmented Code Generation

Kai Ye, Liangcai Su, Chenxiong Qian

2025-09-09

red teaming

2509.07941v1

Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling

Minghui Li, Hao Zhang, Yechao Zhang, Wei Wan, Shengshan Hu, pei Xiaobing, Jing Wang

2025-09-09

red teaming

2509.07617v1

SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs

Hongfei Xia, Hongru Wang, Zeming Liu, Qian Yu, Yuhang Guo, Haifeng Wang

2025-09-09

safety

2509.07315v1

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?

Junjie Mu, Zonghao Ying, Zhekui Fan, Zonglei Jing, Yaoyuan Zhang, Zhengmin Yu, Wenxin Zhang, Quanchen Zou, Xiangzheng Zhang

2025-09-08

red teaming

2509.06350v1

September 08 - September 14, 2025

ENJ: Optimizing Noise with Genetic Algorithms to Jailbreak LSMs

Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding

Prompt Injection Attacks on LLM Generated Reviews of Scientific Publications

Realism Control One-step Diffusion for Real-World Image Super-Resolution

When Your Reviewer is an LLM: Biases, Divergence, and Prompt Injection Risks in Peer Review

Steering MoE LLMs via Expert (De)Activation

Improving LLM Safety and Helpfulness using SFT and DPO: A Study on OPT-350M

PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability

X-Teaming Evolutionary M2S: Automated Discovery of Multi-turn to Single-turn Jailbreak Templates

Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations

ImportSnare: Directed "Code Manual" Hijacking in Retrieval-Augmented Code Generation

Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling

SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?

September 01 - September 07, 2025

Measuring the Vulnerability Disclosure Policies of AI Vendors

Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs

AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMs

EchoLeak: The First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System

Behind the Mask: Benchmarking Camouflaged Jailbreaks in Large Language Models

The LLM Has Left The Chat: Evidence of Bail Preferences in Large Language Models

NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models

Between a Rock and a Hard Place: Exploiting Ethical Reasoning to Jailbreak LLMs

SafeProtein: Red-Teaming Framework and Benchmark for Protein Foundation Models

BioBlue: Notable runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format