Overloading Large Vision-Language Models for Jailbreaking
Large Vision-Language Models (LVLMs) exhibit remarkable vision-language capabilities and are increasingly deployed in real-world applications such as personal assistants, document analysis systems, and embodied agents. However, their dual-modal attack surfaces make them vulnerable to jailbreak attacks. Existing LVLM jailbreaks rely on simple designs, e.g., short text and out-of-distribution images. Nevertheless, recent advancements in both large language model backbones and multimodal mechanisms
Record details
Published: 3 July 2026
Source: arXiv red teaming query
Category: Research
Topics: Safety & alignment · Agents & autonomy
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
A Scalable Approach to Evaluating Moral Sensitivity in LLMs
arXiv · 3 July 2026
CONTRA: Red-Teaming Configurations of Personalizable Agents
arXiv red teaming query · 3 July 2026
When Aggregate Alignment Misleads: Auditing Policy Repair Without Per-State Expert Actions
arXiv · 3 July 2026
Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring
arXiv · 2 July 2026
VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment
arXiv · 2 July 2026
Adversarial Pragmatics for AI Safety Evaluation: A Benchmark for Instruction Conflict, Embedded Commands, and Policy Ambiguity
arXiv · 1 July 2026
How to cite this record
ethics.ai (3 July 2026), “Overloading Large Vision-Language Models for Jailbreaking,” evidence record 3143, https://ethics.ai/record/3143 (originally published by arXiv red teaming query).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.