REVIEW 7 cited by
Safety Alignment for Vision Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Benefiting from the powerful capabilities of Large Language Models (LLMs), pre-trained visual encoder models connected to an LLMs can realize Vision Language Models (VLMs). However, existing research shows that the visual modality of VLMs is vulnerable, with attackers easily bypassing LLMs' safety alignment through visual modality features to launch attacks. To address this issue, we enhance the existing VLMs' visual modality safety alignment by adding safety modules, including a safety projector, safety tokens, and a safety head, through a two-stage training process, effectively improving the model's defense against risky images. For example, building upon the LLaVA-v1.5 model, we achieve a safety score of 8.26, surpassing the GPT-4V on the Red Teaming Visual Language Models (RTVLM) benchmark. Our method boasts ease of use, high flexibility, and strong controllability, and it enhances safety while having minimal impact on the model's general performance. Moreover, our alignment strategy also uncovers some possible risky content within commonly used open-source multimodal datasets. Our code will be open sourced after the anonymous review.
Forward citations
Cited by 7 Pith papers
-
Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions
Hateful optical illusions generated with Stable Diffusion and ControlNet evade current moderation classifiers (best accuracy 0.245) and vision-language models (best accuracy 0.102), with simple image transformations s...
-
$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models
PC2, a multilingual descriptive-rewriting attack, makes GPT-based text-to-image models generate politically controversial images of real public figures despite safety filters.
-
Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities
Vision-language models consistently recognize unsafe content better from text than from images, and a simplified reinforcement learning fine-tune narrows that gap.
-
BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization
A two-stage, objective-decoupled training method embeds visual backdoors into VLA robot policies, achieving near-100% trigger-induced task failure with minimal clean-performance loss in simulation.
-
Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models
HSR restores safety in pruned vision-language models by selectively restoring safety-critical neurons inside the attention heads that matter most for safety.
-
SafeCoT: Improving VLM Safety with Minimal Reasoning
Training vision-language models to emit a short rule-based reasoning chain before refusing improves the safety-usefulness balance, with reported gains even at 100 training samples.
-
Empowering Multimodal LLMs with External Tools: A Comprehensive Survey
A survey paper maps how external tools are used to augment multimodal large language models across data, tasks, evaluation, and future directions.
Discussion (0). Sign in to comment.