Red teaming visual language models
VLMs (Vision-Language Models) extend the capabilities of LLMs (Large Language Models)
to accept multimodal inputs. Since it has been verified that LLMs can be induced to generate
harmful or inaccurate content through specific test cases (termed as Red Teaming), how
VLMs perform in similar scenarios, especially with their combination of textual and visual
inputs, remains a question. To explore this problem, we present a novel red teaming dataset
RTVLM, which encompasses 10 subtasks (eg, image misleading, multi-modal jail-breaking …
to accept multimodal inputs. Since it has been verified that LLMs can be induced to generate
harmful or inaccurate content through specific test cases (termed as Red Teaming), how
VLMs perform in similar scenarios, especially with their combination of textual and visual
inputs, remains a question. To explore this problem, we present a novel red teaming dataset
RTVLM, which encompasses 10 subtasks (eg, image misleading, multi-modal jail-breaking …
VLMs (Vision-Language Models) extend the capabilities of LLMs (Large Language Models) to accept multimodal inputs. Since it has been verified that LLMs can be induced to generate harmful or inaccurate content through specific test cases (termed as Red Teaming), how VLMs perform in similar scenarios, especially with their combination of textual and visual inputs, remains a question. To explore this problem, we present a novel red teaming dataset RTVLM, which encompasses 10 subtasks (e.g., image misleading, multi-modal jail-breaking, face fairness, etc) under 4 primary aspects (faithfulness, privacy, safety, fairness). Our RTVLM is the first red-teaming dataset to benchmark current VLMs in terms of these 4 different aspects. Detailed analysis shows that 10 prominent open-sourced VLMs struggle with the red teaming in different degrees and have up to 31% performance gap with GPT-4V. Additionally, we simply apply red teaming alignment to LLaVA-v1.5 with Supervised Fine-tuning (SFT) using RTVLM, and this bolsters the models' performance with 10% in RTVLM test set, 13% in MM-Hal, and without noticeable decline in MM-Bench, overpassing other LLaVA-based models with regular alignment data. This reveals that current open-sourced VLMs still lack red teaming alignment. Our code and datasets will be open-source.
arxiv.org
以上显示的是最相近的搜索结果。 查看全部搜索结果