Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation
- URL: http://arxiv.org/abs/2403.09572v3
- Date: Mon, 15 Jul 2024 07:03:53 GMT
- Title: Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation
- Authors: Yunhao Gou, Kai Chen, Zhili Liu, Lanqing Hong, Hang Xu, Zhenguo Li, Dit-Yan Yeung, James T. Kwok, Yu Zhang,
- Abstract summary: We propose ECSO (Eyes Closed, Safety On), a training-free protecting approach that exploits the inherent safety awareness of MLLMs.
ECSO generates safer responses via adaptively transforming unsafe images into texts to activate the intrinsic safety mechanism of pre-aligned LLMs.
- Score: 98.02846901473697
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Multimodal large language models (MLLMs) have shown impressive reasoning abilities. However, they are also more vulnerable to jailbreak attacks than their LLM predecessors. Although still capable of detecting the unsafe responses, we observe that safety mechanisms of the pre-aligned LLMs in MLLMs can be easily bypassed with the introduction of image features. To construct robust MLLMs, we propose ECSO (Eyes Closed, Safety On), a novel training-free protecting approach that exploits the inherent safety awareness of MLLMs, and generates safer responses via adaptively transforming unsafe images into texts to activate the intrinsic safety mechanism of pre-aligned LLMs in MLLMs. Experiments on five state-of-the-art (SoTA) MLLMs demonstrate that ECSO enhances model safety significantly (e.g.,, 37.6% improvement on the MM-SafetyBench (SD+OCR) and 71.3% on VLSafe with LLaVA-1.5-7B), while consistently maintaining utility results on common MLLM benchmarks. Furthermore, we show that ECSO can be used as a data engine to generate supervised-finetuning (SFT) data for MLLM alignment without extra human intervention.
Related papers
- Refusing Safe Prompts for Multi-modal Large Language Models [36.276781604895454]
We introduce MLLM-Refusal, the first method that induces refusals for safe prompts.
We formulate MLLM-Refusal as a constrained optimization problem and propose an algorithm to solve it.
We evaluate MLLM-Refusal on four MLLMs across four datasets.
arXiv Detail & Related papers (2024-07-12T07:18:05Z) - Investigating the prompt leakage effect and black-box defenses for multi-turn LLM interactions [125.21418304558948]
leakage in large language models (LLMs) poses a significant security and privacy threat.
leakage in multi-turn LLM interactions along with mitigation strategies has not been studied in a standardized manner.
This paper investigates LLM vulnerabilities against prompt leakage across 4 diverse domains and 10 closed- and open-source LLMs.
arXiv Detail & Related papers (2024-04-24T23:39:58Z) - Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model Security [5.077261736366414]
The pursuit of reliable AI systems like powerful MLLMs has emerged as a pivotal area of contemporary research.
In this paper, we endeavor to demostrate the multifaceted risks associated with the incorporation of image modalities into MLLMs.
arXiv Detail & Related papers (2024-04-08T07:54:18Z) - A New Era in LLM Security: Exploring Security Concerns in Real-World
LLM-based Systems [47.18371401090435]
We analyze the security of Large Language Model (LLM) systems, instead of focusing on the individual LLMs.
We propose a multi-layer and multi-step approach and apply it to the state-of-art OpenAI GPT4.
We found that although the OpenAI GPT4 has designed numerous safety constraints to improve its safety features, these safety constraints are still vulnerable to attackers.
arXiv Detail & Related papers (2024-02-28T19:00:12Z) - ShieldLM: Empowering LLMs as Aligned, Customizable and Explainable
Safety Detectors [93.43498570530565]
ShieldLM is a safety detector for Large Language Models (LLMs) that aligns with general human safety standards.
We show that ShieldLM surpasses strong baselines across four test sets, showcasing remarkable customizability and explainability.
arXiv Detail & Related papers (2024-02-26T09:43:02Z) - The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative [55.08395463562242]
Multimodal Large Language Models (MLLMs) are constantly defining the new boundary of Artificial General Intelligence (AGI)
Our paper explores a novel vulnerability in MLLM societies - the indirect propagation of malicious content.
arXiv Detail & Related papers (2024-02-20T23:08:21Z) - ROSE Doesn't Do That: Boosting the Safety of Instruction-Tuned Large Language Models with Reverse Prompt Contrastive Decoding [89.0074567748505]
We present reverse prompt contrastive decoding (ROSE), a simple-yet-effective method to boost the safety of existing instruction-tuned LLMs without any additional training.
Experiments on 6 safety and 2 general-purpose tasks show that, our ROSE not only brings consistent and significant safety improvements (up to +13.8% safety score) upon 5 types of instruction-tuned LLMs, but also benefits the general-purpose ability of LLMs.
arXiv Detail & Related papers (2024-02-19T06:58:42Z) - MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance [36.03512474289962]
This paper investigates the novel challenge of defending MLLMs against malicious attacks through visual inputs.
Images act as a foreign language" that is not considered during safety alignment, making MLLMs more prone to producing harmful responses.
We introduce MLLM-Protector, a plug-and-play strategy that solves two subtasks: 1) identifying harmful responses via a lightweight harm detector, and 2) transforming harmful responses into harmless ones via a detoxifier.
arXiv Detail & Related papers (2024-01-05T17:05:42Z) - MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models [41.708401515627784]
We observe that Multimodal Large Language Models (MLLMs) can be easily compromised by query-relevant images.
We introduce MM-SafetyBench, a framework designed for conducting safety-critical evaluations of MLLMs against such image-based manipulations.
Our work underscores the need for a concerted effort to strengthen and enhance the safety measures of open-source MLLMs against potential malicious exploits.
arXiv Detail & Related papers (2023-11-29T12:49:45Z)
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.