3 papers
cs.CR2026
Conflicts Make Large Reasoning Models Vulnerable to Attacks
Honghao Liu, Chengjin Xu, Xuhui Jiang +5
Large Reasoning Models (LRMs) have achieved remarkable performance across diverse domains, yet their decision-making under conflicting objectives remains insufficiently understood.…
cs.CR2025
SafeAgentBench: A Benchmark for Safe Task Planning of Embodied LLM Agents
Sheng Yin, Xianghe Pang, Yuanzhuo Ding +7
With the integration of large language models (LLMs), embodied agents have strong capabilities to understand and plan complicated natural language instructions. However, a foreseea…
cs.CV2025
Ethical-Lens: Curbing Malicious Usages of Open-Source Text-to-Image Models
Yuzhu Cai, Sheng Yin, Yuxi Wei +5
The burgeoning landscape of text-to-image models, exemplified by innovations such as Midjourney and DALLE 3, has revolutionized content creation across diverse sectors. However, th…