REVIEW 6 cited by
AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting
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
With the advent and widespread deployment of Multimodal Large Language Models (MLLMs), the imperative to ensure their safety has become increasingly pronounced. However, with the integration of additional modalities, MLLMs are exposed to new vulnerabilities, rendering them prone to structured-based jailbreak attacks, where semantic content (e.g., "harmful text") has been injected into the images to mislead MLLMs. In this work, we aim to defend against such threats. Specifically, we propose \textbf{Ada}ptive \textbf{Shield} Prompting (\textbf{AdaShield}), which prepends inputs with defense prompts to defend MLLMs against structure-based jailbreak attacks without fine-tuning MLLMs or training additional modules (e.g., post-stage content detector). Initially, we present a manually designed static defense prompt, which thoroughly examines the image and instruction content step by step and specifies response methods to malicious queries. Furthermore, we introduce an adaptive auto-refinement framework, consisting of a target MLLM and a LLM-based defense prompt generator (Defender). These components collaboratively and iteratively communicate to generate a defense prompt. Extensive experiments on the popular structure-based jailbreak attacks and benign datasets show that our methods can consistently improve MLLMs' robustness against structure-based jailbreak attacks without compromising the model's general capabilities evaluated on standard benign tasks. Our code is available at https://github.com/rain305f/AdaShield.
Forward citations
Cited by 6 Pith papers
-
SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses
A systemization of LLM jailbreak security that adds linked taxonomies, an evaluation platform, and JailbreakDB, while its main attack–defense comparison results remain deferred.
-
Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack
A two-stage evaluation framework and token-projection analysis show that LVLMs encode harmful semantic cues from images even without OCR, while remaining vulnerable to cross-modal attacks.
-
A Survey on Training-free Alignment of Large Language Models
A survey that catalogs and categorizes training-free LLM alignment methods into pre-decoding, in-decoding, and post-decoding, with a limited experimental comparison on one model.
-
A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations
A survey of LVLM safety that adds a lifecycle taxonomy and new benchmark results showing Janus-Pro-7B has weaker safety than several open-source LVLMs.
-
From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models
The paper argues hallucinations and jailbreaks share the same optimization dynamics and shows that defenses for one also reduce the other, but the theoretical support is largely circular.
-
When Data Manipulation Meets Attack Goals: An In-depth Survey of Attacks for VLMs
A survey that classifies VLM attacks by goal and data manipulation strategy, and reviews defenses and metrics.
Discussion (0). Continue with ORCID to comment.