6 papers
from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors
Yu Yan, Sheng Sun, Zenghao Duan +5
Current studies have exposed the risk of Large Language Models (LLMs) generating harmful content by jailbreak attacks. However, they overlook that the direct generation of harmful…
Red-teaming the Multimodal Reasoning: Jailbreaking Vision-Language Models via Cross-modal Entanglement Attacks
Yu Yan, Sheng Sun, Shengjia Cheng +3
Vision-Language Models (VLMs) with multimodal reasoning capabilities are high-value attack targets, given their potential for handling complex multimodal harmful tasks. Mainstream…
SearchAttack: Red-Teaming LLMs against Knowledge-to-Action Threats under Online Web Search
Yu Yan, Sheng Sun, Mingfeng Li +6
Recently, people have suffered from LLM hallucination and have become increasingly aware of the reliability gap of LLMs in open and knowledge-intensive tasks. As a result, they hav…
Jailbreak-as-a-Service++: Unveiling Distributed AI-Driven Malicious Information Campaigns Powered by LLM Crowdsourcing
Yu Yan, Sheng Sun, Mingfeng Li +6
To prevent the misuse of Large Language Models (LLMs) for malicious purposes, numerous efforts have been made to develop the safety alignment mechanisms of LLMs. However, as multip…
Collaborative Stance Detection via Small-Large Language Model Consistency Verification
Yu Yan, Sheng Sun, Zixiang Tang +2
Stance detection on social media aims to identify attitudes expressed in tweets towards specific targets. Current studies prioritize Large Language Models (LLMs) over Small Languag…
Na'vi or Knave: Jailbreaking Language Models via Metaphorical Avatars
Yu Yan, Sheng Sun, Junqi Tong +2
Metaphor serves as an implicit approach to convey information, while enabling the generalized comprehension of complex subjects. However, metaphor can potentially be exploited to b…