arXiv Computation and Language August 25, 2026 By Wenyun Li, Guiping Cao, Xiangyuan Lan, Zheng Zhang

Text-Anchored Semantic Perturbations for Transferable Jailbreak Attacks on Multimodal Large Language Models

Read the original on arXiv Computation and Language →

The paper introduces TA-SPA, a black‑box jailbreak method for multimodal large language models that generates transferable perturbations in a text‑anchored semantic space. It combines Text‑Anchored Semantic Factorization (TASF) to separate cross‑modal semantic factors from modality‑specific residuals with Semantic‑Preserving Augmentation (SPA) to diversify harmful target anchors while maintaining semantic consistency. Experiments demonstrate strong attack effectiveness and transferability to commercial MLLMs, with competitive performance against representative defenses.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Hugging Face Trending Papers

Aug 23

Text-Anchored Semantic Perturbations for Transferable Jailbreak Attacks on Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language interaction, yet their safety alignment remains vulnerable to jailbreak attacks. A key challenge is that s...

llms multimodal safety

arXiv AI

Jun 2

Jailbreaking Multimodal Large Language Models using Multi-Clip Video

arXiv:2606. 02111v1 Announce Type: cross Abstract: As multimodal large language models (MLLMs) have advanced to process video inputs, concerns have emerged about their potential for malicious misuse.

By Choongwon Kang, Seungjong Sun, Hyunmin Jun, Jang Hyun Kim

llms multimodal safety

arXiv AI

Sep 1

Robustness of Vision Language Models Against Split-Image Harmful Input Attacks

arXiv:2602.08136v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic...

By Md Rafi Ur Rashid, MD Sadik Hossain Shanto, Vishnu Asutosh Dasu, Shagufta Mehnaz

llms reinforcement-learning fine-tuning efficiency multimodal benchmarks safety

arXiv AI

Aug 24

ReFrame: Evidence-Guided Test-Time Safety Alignment in Multimodal Large Language Models

ReFrame is a training‑free framework that enhances safety alignment for multimodal large language models at test time. It uses two lightweight agents: one generates risk and utility evidence, and the other rewrites prompts and routes images to create a safe proxy before invoking the deployed MLLM. Experiments show that ReFrame improves jailbreak defense, safety awareness, and reduces over‑sensitivity while maintaining multimodal utility.

By Wenzheng Jiang, Xuankun Rong, Yuanzhao Zhai, Dawei Feng, Huaimin Wang

llms agents multimodal benchmarks safety

arXiv AI

Sep 10

SAFEGuard: Detect Optimization-Based Jailbreak Attacks Through Harmful Semantic Analysis and Fluency Measurement

arXiv:2609.05850v1 Announce Type: cross Abstract: Despite the significant efforts devoted to aligning large language models (LLMs) with human values and ensuring safe deployment, recent work has reve...

By Quoc Viet Vo, Trung Le, Damith C. Ranasinghe, Ehsan Abbasnejad

llms benchmarks safety

arXiv Machine Learning

Sep 11

Understanding In-Context Multimodal Jailbreaks via Posterior Reweighting

The paper introduces a posterior reweighting framework to explain and counter in-context learning jailbreaks in multimodal large language models. It models the model as switching between safe and harmful behavioral modes, interpreting prompt demonstrations as evidence that shifts the posterior. Using this view, the authors derive scaling laws for jailbreak effectiveness and propose a defense that injects benign counter‑evidence to suppress harmful drift while maintaining utility.

By Xu Zhang, Dev Mistry, Xiang Xu, Ren Wang

llms multimodal safety

One email a morning, machine-written

Related stories

Text-Anchored Semantic Perturbations for Transferable Jailbreak Attacks on Multimodal Large Language Models

Jailbreaking Multimodal Large Language Models using Multi-Clip Video

Robustness of Vision Language Models Against Split-Image Harmful Input Attacks

ReFrame: Evidence-Guided Test-Time Safety Alignment in Multimodal Large Language Models

SAFEGuard: Detect Optimization-Based Jailbreak Attacks Through Harmful Semantic Analysis and Fluency Measurement

Understanding In-Context Multimodal Jailbreaks via Posterior Reweighting