REVIEW 6 cited by
Stop Reasoning! When Multimodal LLM with Chain-of-Thought Reasoning Meets Adversarial Image
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 LLMs (MLLMs) with a great ability of text and image understanding have received great attention. To achieve better reasoning with MLLMs, Chain-of-Thought (CoT) reasoning has been widely explored, which further promotes MLLMs' explainability by giving intermediate reasoning steps. Despite the strong power demonstrated by MLLMs in multimodal reasoning, recent studies show that MLLMs still suffer from adversarial images. This raises the following open questions: Does CoT also enhance the adversarial robustness of MLLMs? What do the intermediate reasoning steps of CoT entail under adversarial attacks? To answer these questions, we first generalize existing attacks to CoT-based inferences by attacking the two main components, i.e., rationale and answer. We find that CoT indeed improves MLLMs' adversarial robustness against the existing attack methods by leveraging the multi-step reasoning process, but not substantially. Based on our findings, we further propose a novel attack method, termed as stop-reasoning attack, that attacks the model while bypassing the CoT reasoning process. Experiments on three MLLMs and two visual reasoning datasets verify the effectiveness of our proposed method. We show that stop-reasoning attack can result in misled predictions and outperform baseline attacks by a significant margin.
Forward citations
Cited by 6 Pith papers
-
On Adversarial Vulnerability of Vision-Language Models through the Lens of Intermediate Spectral Subspaces
Aligning adversarial perturbations with the near-null singular directions of intermediate linear layers in transformer VLMs yields stronger attacks than existing feature- and output-space methods.
-
Can Large Multimodal Models Actively Recognize Faulty Inputs? A Systematic Evaluation Framework of Their Input Scrutiny Ability
Large multimodal models mostly fail to proactively detect flawed textual premises, and their performance depends on error type and on how they weight text versus images.
-
AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery
Fake 'Close AD' ads make VLM web agents click them over 60% of the time, and near 100% in some settings.
-
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.
-
Standardization of Neuromuscular Reflex Analysis -- Role of Fine-Tuned Vision-Language Model Consortium and OpenAI gpt-oss Reasoning LLM Enabled Decision Support System
A consortium of fine-tuned VLMs plus a reasoning LLM is proposed for H-reflex image analysis, but the claimed high accuracy is backed only by anecdotal examples.
-
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.