Papers by Lyucheng Wu
Automating Steering for Safe Multimodal Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in Multimodal Large Language Models (MLLMs) have unlocked powerful cross-modal reasoning abilities, but also raised new safety concerns, especially when faced with adversarial multimodal inputs. |
| Approach: | They propose a modular and adaptive inference-time intervention technology, AutoSteer, that integrates a safety awareness score, an adaptive safety prober, and a lightweight Refusal Head to modulate generation when safety risks are detected. |
| Outcome: | Experiments on LLaVA-OV and Chameleon show that AutoSteer significantly reduces the Attack Success Rate (ASR) for textual, visual, and cross-modal threats while maintaining general abilities. |