Ask, Attend, Attack: A Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models

Q Zeng, Z Wang, Y Cheung, M Jiang - arXiv preprint arXiv:2408.08989, 2024 - arxiv.org
While image-to-text models have demonstrated significant advancements in various vision-
language tasks, they remain susceptible to adversarial attacks. Existing white-box attacks on …

LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models

M Yu, J Fang, Y Zhou, X Fan, K Wang, S Pan… - arXiv preprint arXiv …, 2024 - arxiv.org
While safety-aligned large language models (LLMs) are increasingly used as the
cornerstone for powerful systems such as multi-agent frameworks to solve complex real …

Enhancing Large-scale UAV Route Planing with Global and Local Features via Reinforcement Graph Fusion

T Zhou, K Ye, Z Shi, J Lin, D Xu, M Jiang - arXiv preprint arXiv:2412.15537, 2024 - arxiv.org
Numerous remarkable advancements have been made in accuracy, speed, and parallelism
for solving the Unmanned Aerial Vehicle Route Planing (UAVRP). However, existing …