4 papers
MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs
Yilian Liu, Xiaojun Jia, Guoshun Nan +6
Multimodal Large Language Models (MLLMs) have achieved remarkable performance but remain vulnerable to jailbreak attacks that can induce harmful content and undermine their secure…
CODE: A Contradiction-Based Deliberation Extension Framework for Overthinking Attacks on Retrieval-Augmented Generation
Xiaolei Zhang, Xiaojun Jia, Liquan Chen +1
Introducing reasoning models into Retrieval-Augmented Generation (RAG) systems enhances task performance through step-by-step reasoning, logical consistency, and multi-step self-ve…
Knowledge-Driven Multi-Turn Jailbreaking on Large Language Models
Songze Li, Ruishi He, Xiaojun Jia +2
Large Language Models (LLMs) face a significant threat from multi-turn jailbreak attacks, where adversaries progressively steer conversations to elicit harmful outputs. However, th…
Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography
Songze Li, Jiameng Cheng, Yiming Li +2
By integrating language understanding with perceptual modalities such as images, multimodal large language models (MLLMs) constitute a critical substrate for modern AI systems, par…