Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025
This work addresses safety threats for MLLM users by providing systematic evaluation and guidance, though it is incremental as it builds on existing safety concerns without introducing new methods.
The paper tackled the problem of safety vulnerabilities in Multimodal Large Language Models (MLLMs) by organizing the ATLAS Challenge 2025, involving 86 teams to test MLLM vulnerabilities through adversarial attacks, establishing new benchmarks for safety evaluation.
Multimodal Large Language Models (MLLMs) have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks that induce harmful outputs. To systematically evaluate and improve their safety, we organized the Adversarial Testing & Large-model Alignment Safety Grand Challenge (ATLAS) 2025}. This technical report presents findings from the competition, which involved 86 teams testing MLLM vulnerabilities via adversarial image-text attacks in two phases: white-box and black-box evaluations. The competition results highlight ongoing challenges in securing MLLMs and provide valuable guidance for developing stronger defense mechanisms. The challenge establishes new benchmarks for MLLM safety evaluation and lays groundwork for advancing safer multimodal AI systems. The code and data for this challenge are openly available at https://github.com/NY1024/ATLAS_Challenge_2025.