PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality
Safeguarding vision-language models (VLMs) is a critical challenge, as existing methods often suffer from over-defense, which harms utility, or rely on shallow alignment, failing to detect complex threats that require deep reasoning. To this end, we introduc PRISM (Principled Reasoning for Integrated Safety in Multimodality), a System 2-like framework that aligns VLMs through a structured four-stage reasoning process explicitly designed to handle three distinct categories of multimodal safety violations. Our framework consists of two key components: a structured reasoning pipeline that analyzes each violation category in dedicated stages, and PRISM-DPO, generated via Monte Carlo Tree Search (MCTS) to refine reasoning quality through Direct Preference Optimization. Comprehensive evaluations show that PRISM substantially reduces attack success rates on JailbreakV-28K and VLBreak, improves robustness against adaptive attacks, and generalizes to out-of-distribution multi-image threats, while better preserving model utility on benign multimodal benchmarks. Our code, data, and model weights available at https://github.com/SaFoLab-WISC/PRISM.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Alignment-Weighted DPO: A principled reasoning approach to improve safety alignment
Recent advances in alignment techniques such as Supervised Fine-Tuning (SFT), Reinforcement Learning from Human Feedback (RLHF), and Direct Preference Optimization (DPO) have improved the safety of large language models …
Reinforcement LearningExpert Personas Improve LLM Alignment but Damage Accuracy: Bootstrapping Intent-Based Persona Routing with PRISM
Persona prompting can steer LLM generation towards a domain-specific tone and pattern. This behavior enables use cases in multi-agent systems where diverse interactions are crucial and human-centered tasks require high-l…
Large Reasoning Models Learn Better Alignment from Flawed Thinking
Large reasoning models (LRMs) "think" by generating structured chain-of-thought (CoT) before producing a final answer, yet they still lack the ability to reason critically about safety alignment and are easily biased whe…
Reinforcement LearningPRISM: Prosody-Integrated Multi-Agent Reasoning Framework for Empathetic Spoken Dialogue
Empathetic spoken dialogue systems require not only semantically appropriate responses but also emotionally aligned prosodic expression. However, cascade pipelines often discard acoustic cues during speech-to-text conver…
Dialogue GenerationResponse GenerationSpeech SynthesisBeyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
The standard post-training recipe for large multimodal models (LMMs) applies supervised fine-tuning (SFT) on curated demonstrations followed by reinforcement learning with verifiable rewards (RLVR). However, SFT introduc…
Reinforcement LearningMultimodal ReasoningVisual Grounding