Cross-Modal Safety Alignment: Is textual unlearning all you need?

• URL: http://arxiv.org/abs/2406.02575v1
• Date: Mon, 27 May 2024 20:29:13 GMT
• Title: Cross-Modal Safety Alignment: Is textual unlearning all you need?
• Authors: Trishna Chakraborty, Erfan Shayegani, Zikui Cai, Nael Abu-Ghazaleh, M. Salman Asif, Yue Dong, Amit K. Roy-Chowdhury, Chengyu Song,
• Abstract summary: We show that unlearning solely in the textual domain can be effective for cross-modality safety alignment. Our experiments show that unlearning with a multi-modal dataset offers no potential benefits but incurs significantly increased computational demands.
• Score: 36.29740845754985
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT) and Reinforcement Learning with Human Feedback (RLHF). While further SFT and RLHF-based safety training can be conducted in multi-modal settings, collecting multi-modal training datasets poses a significant challenge. Inspired by the structural design of recent multi-modal models, where, regardless of the combination of input modalities, all inputs are ultimately fused into the language space, we aim to explore whether unlearning solely in the textual domain can be effective for cross-modality safety alignment. Our evaluation across six datasets empirically demonstrates the transferability -- textual unlearning in VLMs significantly reduces the Attack Success Rate (ASR) to less than 8\% and in some cases, even as low as nearly 2\% for both text-based and vision-text-based attacks, alongside preserving the utility. Moreover, our experiments show that unlearning with a multi-modal dataset offers no potential benefits but incurs significantly increased computational demands, possibly up to 6 times higher.

Related papers

• Multi-Stage Knowledge Integration of Vision-Language Models for Continual Learning [79.46570165281084]
  We propose a Multi-Stage Knowledge Integration network (MulKI) to emulate the human learning process in distillation methods. MulKI achieves this through four stages, including Eliciting Ideas, Adding New Ideas, Distinguishing Ideas, and Making Connections. Our method demonstrates significant improvements in maintaining zero-shot capabilities while supporting continual learning across diverse downstream tasks.
  arXiv  Detail & Related papers  (2024-11-11T07:36:19Z)
• LLMs Can Evolve Continually on Modality for X-Modal Reasoning [62.2874638875554]
  Existing methods rely heavily on modal-specific pretraining and joint-modal tuning, leading to significant computational burdens when expanding to new modalities. We propose PathWeave, a flexible and scalable framework with modal-Path sWitching and ExpAnsion abilities. PathWeave performs comparably to state-of-the-art MLLMs while concurrently reducing parameter training burdens by 98.73%.
  arXiv  Detail & Related papers  (2024-10-26T13:19:57Z)
• Cross-Modal Few-Shot Learning: a Generative Transfer Learning Framework [58.362064122489166]
  This paper introduces the Cross-modal Few-Shot Learning task, which aims to recognize instances from multiple modalities when only a few labeled examples are available. We propose a Generative Transfer Learning framework consisting of two stages: the first involves training on abundant unimodal data, and the second focuses on transfer learning to adapt to novel data. Our finds demonstrate that GTL has superior performance compared to state-of-the-art methods across four distinct multi-modal datasets.
  arXiv  Detail & Related papers  (2024-10-14T16:09:38Z)
• Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models [26.83278034227966]
  The safety alignment ability of Vision-Language Models (VLMs) is prone to be degraded by the integration of the vision module. We show that the challenge arises from the representation gap that emerges when introducing vision modality to VLMs. To reduce safety alignment degradation, we introduce Cross-Modality Representation Manipulation (CMRM)
  arXiv  Detail & Related papers  (2024-10-11T17:59:31Z)
• NVLM: Open Frontier-Class Multimodal LLMs [64.00053046838225]
  We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks. We propose a novel architecture that enhances both training efficiency and multimodal reasoning capabilities. We develop production-grade multimodality for the NVLM-1.0 models, enabling them to excel in vision-language tasks.
  arXiv  Detail & Related papers  (2024-09-17T17:59:06Z)
• Visual Prompt Flexible-Modal Face Anti-Spoofing [23.58674017653937]
  multimodal face data collected from the real world is often imperfect due to missing modalities from various imaging sensors. We propose flexible-modal FAS, which learns the modal-relevant prompts to adapt the frozen pre-trained foundation model to downstream flexible-modal FAS task. experiments conducted on two multimodal FAS benchmark datasets demonstrate the effectiveness of our VP-FAS framework.
  arXiv  Detail & Related papers  (2023-07-26T05:06:41Z)
• RC3: Regularized Contrastive Cross-lingual Cross-modal Pre-training [84.23022072347821]
  We propose a regularized cross-lingual visio-textual contrastive learning objective that constrains the representation proximity of weakly-aligned visio-textual inputs. Experiments on 5 downstream multi-modal tasks across 6 languages demonstrate the effectiveness of our proposed method.
  arXiv  Detail & Related papers  (2023-05-13T14:41:05Z)
• Efficient Multimodal Transformer with Dual-Level Feature Restoration for Robust Multimodal Sentiment Analysis [47.29528724322795]
  Multimodal Sentiment Analysis (MSA) has attracted increasing attention recently. Despite significant progress, there are still two major challenges on the way towards robust MSA. We propose a generic and unified framework to address them, named Efficient Multimodal Transformer with Dual-Level Feature Restoration (EMT-DLFR)
  arXiv  Detail & Related papers  (2022-08-16T08:02:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.