EUVD-2026-4711

vLLM vulnerable to Server-Side Request Forgery SSRF through MediaConnector...

CVE-2026-22773

A flaw was found in vLLM, an inference and serving engine for large language models LLMs. A remote attacker can exploit this vulnerability by sending a specially crafted 1x1 pixel image to a vLLM engine serving multimodal models that use the Idefics3 vision model implementation. This leads to a...

FOCA: Multimodal Malware Classification Via Hyperbolic Cross-Attention

In this work, we introduce FOCA, a novel multimodal framework for malware classification that jointly leverages audio and visual modalities. Unlike conventional Euclidean-based fusion methods, FOCA is the first to exploit the intrinsic hierarchical relationships between audio and visual...

EUVD-2026-1865

vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions...

Integrating APK Image and Text Data for Enhanced Threat Detection: A Multimodal Deep Learning Approach to Android Malware

As zero-day Android malware attacks grow more sophisticated, recent research highlights the effectiveness of using image-based representations of malware bytecode to detect previously unseen threats. However, existing studies often overlook how image type and resolution affect detection and ignor...

Use of NullPointerException Catch to Detect NULL Pointer Dereference

Overview Affected versions of this package are vulnerable to Use of NullPointerException Catch to Detect NULL Pointer Dereference in the MultimodalTokenize function that improperly processes NULL from mtmdhelperbitmapinitfrombuf function of vendored llama.cpp. An attacker can cause the applicatio...

Ollama 安全漏洞

Ollama is an Ollama open source large-scale language model that can be started and run locally. A security vulnerability exists in Ollama versions 0.11.5-rc0 through 0.13.5, which stems from the presence of a null pointer dereference in the image processing function of the multimodal model, which...

PYSEC-2026-143

vLLM is an inference and serving engine for large language models LLMs. In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine serving multimodal models that use the Idefics3 vision model implementation by sending a specially crafted 1x1 pixel image. This causes a tensor dimensi...

CVE-2026-22773

vLLM is an inference and serving engine for large language models LLMs. In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine serving multimodal models that use the Idefics3 vision model implementation by sending a specially crafted 1x1 pixel image. This causes a tensor dimensi...

PYSEC-2026-143

vLLM is an inference and serving engine for large language models LLMs. In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine serving multimodal models that use the Idefics3 vision model implementation by sending a specially crafted 1x1 pixel image. This causes a tensor dimensi...

CVE-2026-22773 vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions

vLLM is an inference and serving engine for large language models LLMs. In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine serving multimodal models that use the Idefics3 vision model implementation by sending a specially crafted 1x1 pixel image. This causes a tensor dimensi...

CVE-2026-22773

CVE-2026-22773 affects vLLM (inference/serving engine) versions 0.6.4 through before 0.12.0 that serve multimodal models using the Idefics3 vision model. A crafted 1x1 pixel image triggers a tensor dimension mismatch in the image input processing, causing an unhandled runtime error and enabling a...

CVE-2026-22773 vLLM is vulnerable to DoS in Idefics3 vision models via image payload with ambiguous dimensions

vLLM is an inference and serving engine for large language models LLMs. In versions from 0.6.4 to before 0.12.0, users can crash the vLLM engine serving multimodal models that use the Idefics3 vision model implementation by sending a specially crafted 1x1 pixel image. This causes a tensor dimensi...

PT-2026-2260

Name of the Vulnerable Software and Affected Versions vLLM versions 0.6.4 through 0.11.9 Description vLLM is an inference and serving engine for large language models LLMs. Users can cause the vLLM engine to crash when serving multimodal models that utilize the Idefics3 vision model implementatio...

Multi-Turn Jailbreaking Attack in Multi-Modal Large Language Models

In recent years, the security vulnerabilities of Multi-modal Large Language Models MLLMs have become a serious concern in the Generative Artificial Intelligence GenAI research. These highly intelligent models, capable of performing multi-modal tasks with high accuracy, are also severely susceptib...

Jailbreaking LLMs and VLMs: Mechanisms, Evaluation, and Unified Defense

This paper provides a systematic survey of jailbreak attacks and defenses on Large Language Models LLMs and Vision-Language Models VLMs, emphasizing that jailbreak vulnerabilities stem from structural factors such as incomplete training data, linguistic ambiguity, and generative uncertainty. It...

Focus on What Matters: Fisher-Guided Adaptive Multimodal Fusion for Vulnerability Detection

Software vulnerability detection is a critical task for securing software systems and can be formulated as a binary classification problem: given a code snippet, determine whether it contains a vulnerability. Existing multimodal approaches typically fuse Natural Code Sequence NCS representations...

OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs

The rapid integration of Multimodal Large Language Models MLLMs into critical applications is increasingly hindered by persistent safety vulnerabilities. However, existing red-teaming benchmarks are often fragmented, limited to single-turn text interactions, and lack the scalability required for...

Toward Trustworthy Agentic AI: A Multimodal Framework for Preventing Prompt Injection Attacks

Powerful autonomous systems, which reason, plan, and converse using and between numerous tools and agents, are made possible by Large Language Models LLMs, Vision-Language Models VLMs, and new agentic AI systems, like LangChain and GraphChain. Nevertheless, this agentic environment increases the...

Multi-Agent Framework for Threat Mitigation and Resilience in AI-Based Systems

Machine learning ML underpins foundation models in finance, healthcare, and critical infrastructure, making them targets for data poisoning, model extraction, prompt injection, automated jailbreaking, and preference-guided black-box attacks that exploit model comparisons. Larger models can be mor...