9 papers
Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
Yunhao Chen, Xin Wang, Juncheng Li +5
Automated red teaming frameworks for Large Language Models (LLMs) have become increasingly sophisticated, yet many still formulate attack optimization primarily in the prompt space…
MathGen: Revealing the Illusion of Mathematical Competence through Text-to-Image Generation
Ruiyao Liu, Hui Shen, Ping Zhang +16
Modern generative models have demonstrated the ability to solve challenging mathematical problems. In many real-world settings, however, mathematical solutions must be expressed vi…
When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG
Junchen Li, Chao Qi, Rongzheng Wang +7
Retrieval-Augmented Generation (RAG) systems are vulnerable to blocking attacks, in which poisoned documents cause large language models (LLMs) to refuse benign queries. Existing a…
OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs
Xin Wang, Yunhao Chen, Juncheng Li +7
The rapid integration of Multimodal Large Language Models (MLLMs) into critical applications is increasingly hindered by persistent safety vulnerabilities. However, existing red-te…
BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
Juncheng Li, Yige Li, Hanxun Huang +5
Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously activated at inference time. While…
IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves
Ruofan Wang, Juncheng Li, Yixu Wang +6
As large Vision-Language Models (VLMs) gain prominence, ensuring their safe deployment has become critical. Recent studies have explored VLM robustness against jailbreak attacks-te…