REVIEW 6 cited by
Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
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
Multimodal Large Language Models (MLLMs) have achieved impressive performance and have been put into practical use in commercial applications, but they still have potential safety mechanism vulnerabilities. Jailbreak attacks are red teaming methods that aim to bypass safety mechanisms and discover MLLMs' potential risks. Existing MLLMs' jailbreak methods often bypass the model's safety mechanism through complex optimization methods or carefully designed image and text prompts. Despite achieving some progress, they have a low attack success rate on commercial closed-source MLLMs. Unlike previous research, we empirically find that there exists a Shuffle Inconsistency between MLLMs' comprehension ability and safety ability for the shuffled harmful instruction. That is, from the perspective of comprehension ability, MLLMs can understand the shuffled harmful text-image instructions well. However, they can be easily bypassed by the shuffled harmful instructions from the perspective of safety ability, leading to harmful responses. Then we innovatively propose a text-image jailbreak attack named SI-Attack. Specifically, to fully utilize the Shuffle Inconsistency and overcome the shuffle randomness, we apply a query-based black-box optimization method to select the most harmful shuffled inputs based on the feedback of the toxic judge model. A series of experiments show that SI-Attack can improve the attack's performance on three benchmarks. In particular, SI-Attack can obviously improve the attack success rate for commercial MLLMs such as GPT-4o or Claude-3.5-Sonnet.
Forward citations
Cited by 6 Pith papers
-
Self-Aware Safety Augmentation: Leveraging Internal Semantic Understanding to Enhance Safety in Vision-Language Models
A tuning-free method that projects middle-layer semantic representations back onto early safety layers, improving vision-language model safety with minimal utility loss.
-
VLMs Can Aggregate Scattered Training Patches
Open-source VLMs can infer image IDs or safety labels after training only on scattered patches of those images, a capability that can be abused to bypass image moderation.
-
AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders
AMIA is an inference-only jailbreak defense that masks text-irrelevant image patches and prompts single-pass intention analysis, lifting average defense success on LVLMs from 52.4% to 81.7%.
-
Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models
IJA hides a malicious instruction in image steganography and uses a benign extraction prompt plus iterative template refinement to make multimodal LLMs execute it.
-
Trojan Horse Prompting: Jailbreaking Conversational Multimodal Models by Forging Assistant Message
Trojan Horse Prompting injects malicious instructions into a fabricated assistant message in the API chat history, aiming to bypass Gemini's safety filters, but no quantitative evidence is provided.
-
A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination
A new jailbreak framework, HACA, combines atomic text and image attack strategies selected by a cross-modal planner and generates attacks with LLMs and text-to-image models, reaching 95.48% average attack success acro...
Discussion (0). Continue with ORCID to comment.