6 papers
SeedAIchemy: LLM-Driven Seed Corpus Generation for Fuzzing
Aidan Wen, Norah A. Alzahrani, Jingzhi Jiang +5
We introduce SeedAIchemy, an automated LLM-driven corpus generation tool that makes it easier for developers to implement fuzzing effectively. SeedAIchemy consists of five modules…
Defending Against Prompt Injection with DataFilter
Yizhu Wang, Sizhe Chen, Raghad Alkhudair +2
When large language model (LLM) agents are increasingly deployed to automate tasks and interact with untrusted external data, prompt injection emerges as a significant security thr…
PromptArmor: Simple yet Effective Prompt Injection Defenses
Tianneng Shi, Kaijie Zhu, Zhun Wang +13
Despite their potential, recent research has demonstrated that LLM agents are vulnerable to prompt injection attacks, where malicious prompts are injected into the agent's input, c…
JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift
Julien Piet, Xiao Huang, Dennis Jacob +7
Safety and security remain critical concerns in AI deployment. Despite safety training through reinforcement learning with human feedback (RLHF) [ 32], language models remain vulne…
PromptShield: Deployable Detection for Prompt Injection Attacks
Dennis Jacob, Hend Alzahrani, Zhanhao Hu +2
Application designers have moved to integrate large language models (LLMs) into their products. However, many LLM-integrated applications are vulnerable to prompt injections. While…
Can LLMs Ask Good Questions?
Yueheng Zhang, Xiaoyuan Liu, Yiyou Sun +5
We evaluate questions generated by large language models (LLMs) from context, comparing them to human-authored questions across six dimensions: question type, question length, cont…