arXiv AI

Semantic Router: On the Feasibility of Hijacking MLLMs via a Single Adversarial Perturbation

arXiv:2511. 20002v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed in stateless systems, such as autonomous driving and robotics.

arXiv Machine Learning

Jun 30

High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models

arXiv:2512. 21815v4 Announce Type: replace-cross Abstract: Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks.

By Mengqi He, Xinyu Tian, Xin Shen, Jinhong Ni, Shu Zou, Zhaoyuan Yang, Jing Zhang

llms multimodal safety

arXiv AI

Jun 16

Forced Deferral: Manipulating Routing Decisions in Multimodal LLM Cascades

arXiv:2606. 15308v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) have shown strong visual reasoning abilities, serving a large model for every query is computationally expensive.

By Zhongye Liu, Yaopei Zeng, Yurui Chang, Lu Lin

llms multimodal safety

arXiv Machine Learning

Jun 5

Steering Vectors are an Adversarial Attack Surface

arXiv:2606. 05958v1 Announce Type: new Abstract: Activation steering has become a popular way to control Large Language Model (LLM) behavior without fine-tuning.

By Abzal Aidakhmetov, Donato Crisostomi, Tommaso Mencattini, Adrian Robert Minut, Iacopo Masi, Emanuele Rodol\`a

llms fine-tuning multimodal safety

arXiv AI

Jun 24

PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models

arXiv:2606. 24388v1 Announce Type: new Abstract: We introduce a large-scale, open-source dataset of pre-generated adversarial attacks for vision-language models (VLMs).

By Simone Gallivanone, Hossein Khodadadi, Mauro Dore, Mauro Medda, Nicola Franco

llms fine-tuning multimodal benchmarks safety

arXiv Machine Learning

6d ago

LLM Router: Rethinking Routing with Prefill Activations

arXiv:2603. 20895v3 Announce Type: replace-cross Abstract: Existing routers rely on semantic query features or handcrafted features, which often fail to capture model-specific failures or intrinsic task difficulty.

By Tanay Varshney, Annie Surla, Michelle Xu, Gomathy Venkata Krishnan, Maximilian Jeblick, David Austin, Neal Vaidya, Davide Onofrio

llms

arXiv Machine Learning

Aug 11

Preference Redirection via Attention Concentration: An Attack on Computer Use Agents

arXiv:2604. 08005v2 Announce Type: replace Abstract: Advancements in multimodal foundation models have enabled the development of Computer Use Agents (CUAs) capable of autonomously interacting with GUI environments.

By Dominik Seip, Matthias Hein

agents fine-tuning multimodal safety

arXiv AI

Jun 3

Inference Cost Attacks for Retrieval-Augmented Large Language Models

arXiv:2606. 02643v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG)-enhanced LLM systems, while powerful, introduce substantial inference costs due to the inclusion of an extra multi-stage pipeline that dynamically retrieves and synthesizes information from external knowledge sources.

By Chengliang Liu, Liangbo Ning, Yujuan Ding, Wenqi Fan

llms rag agents reinforcement-learning robotics safety

arXiv Machine Learning

Jul 23

Don't Fool Me Twice: Adapting to Adversity in the Wild with Experience-Driven Reasoning

arXiv:2605. 31119v2 Announce Type: replace-cross Abstract: In robotics, dangers and adversity modes are often embodiment-specific and relative to each agent.

By Navin Sriram Ravie, Andrew Jong, Krrish Jain, John Liu, Omar Alama, Bijo Sebastian, Sebastian Scherer

llms agents robotics multimodal

arXiv AI

Jun 2

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations

arXiv:2605. 12813v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve strong performance across many tasks but remain vulnerable to hallucinations, making it important to systematically evaluate their reliability under realistic adversarial inputs.

By Buyun Liang, Jinqi Luo, Liangzu Peng, Kwan Ho Ryan Chan, Darshan Thaker, Kaleab A. Kinfu, Fengrui Tian, Hamed Hassani, Ren\'e Vidal

llms diffusion benchmarks safety

arXiv AI

Jul 29

Architectural Backdoors in Vision-Language Model Supply Chains via Representation Steering

arXiv:2607. 25479v1 Announce Type: cross Abstract: Vision--Language Models (VLMs) are increasingly deployed through a model supply chain in which pretrained checkpoints, architecture definitions, text encoders, and exported computation graphs are distributed by third parties and reused across downstream services.

By Maria Rosaria Briglia, Igor Maljkovic, Antonio Emanuele Cin\`a, Luca Oneto, Iacopo Masi, Fabio Roli

llms rag diffusion nlp fine-tuning multimodal safety

arXiv AI

Jul 23

Matching Ranks Over Probability Yields Truly Deep Safety Alignment

arXiv:2512. 05518v2 Announce Type: replace-cross Abstract: Open-source Large Language Models (LLMs) play a critical role in the democratization of AI, yet their "open" nature introduces more avenues for malicious actors to misuse them for harmful purposes.

By Jason Vega, Gagandeep Singh

llms fine-tuning safety

arXiv AI

Jun 8

EVA: Evolving Semantic Adversaries for Red-Teaming GUI Agents Against Environmental Injection Attacks

arXiv:2505. 14289v2 Announce Type: replace Abstract: Graphical User Interface (GUI) agents powered by Multimodal Large Language Models (MLLMs) are increasingly deployed yet vulnerable to Environmental Injection Attacks (EIAs).

By Yijie Lu, Manman Zhao, Tianjie Ju, Zihe Yan, Xinbei Ma, Yuan Guo, Daizong Ding, Gongshen Liu, Zhuosheng Zhang

llms agents multimodal safety

Related stories