Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses

Multimodal large language models MLLMs comprise of both visual and textual modalities to process vision language tasks. However, MLLMs are vulnerable to security-related issues, such as jailbreak attacks that alter the model's input to induce unauthorized or harmful responses. The incorporation o...

Beyond Text: Multimodal Jailbreaking of Vision-Language and Audio Models through Perceptually Simple Transformations

Multimodal large language models MLLMs have achieved remarkable progress, yet remain critically vulnerable to adversarial attacks that exploit weaknesses in cross-modal processing. We present a systematic study of multimodal jailbreaks targeting both vision-language and audio-language models,...

CrossGuard: Safeguarding MLLMs against Joint-Modal Implicit Malicious Attacks

Multimodal Large Language Models MLLMs achieve strong reasoning and perception capabilities but are increasingly vulnerable to jailbreak attacks. While existing work focuses on explicit attacks, where malicious content resides in a single modality, recent studies reveal implicit attacks, in which...

Multimodal Safety Is Asymmetric: Cross-Modal Exploits Unlock Black-Box MLLMs Jailbreaks

Multimodal large language models MLLMs have demonstrated significant utility across diverse real-world applications. But MLLMs remain vulnerable to jailbreaks, where adversarial inputs can collapse their safety constraints and trigger unethical responses. In this work, we investigate jailbreaks i...

Countermind: A Multi-Layered Security Architecture for Large Language Models

The security of Large Language Model LLM applications is fundamentally challenged by "form-first" attacks like prompt injection and jailbreaking, where malicious instructions are embedded within user inputs. Conventional defenses, which rely on post hoc output filtering, are often brittle and fai...

VisualDAN: Exposing Vulnerabilities in VLMs with Visual-Driven DAN Commands

Vision-Language Models VLMs have garnered significant attention for their remarkable ability to interpret and generate multimodal content. However, securing these models against jailbreak attacks continues to be a substantial challenge. Unlike text-only models, VLMs integrate additional modalitie...

GHSA-3F6C-7FW2-PPM4 vLLM is vulnerable to Server-Side Request Forgery (SSRF) through `MediaConnector` class

Summary A Server-Side Request Forgery SSRF vulnerability exists in the MediaConnector class within the vLLM project's multimodal feature set. The loadfromurl and loadfromurlasync methods fetch and process media from user-provided URLs without adequate restrictions on the target hosts. This allows...

CVE-2025-6242

The CVE-2025-6242 SSRF vulnerability targets vLLM's MediaConnector (load_from_url/load_from_url_async) allowing user-supplied URLs to trigger server-side requests to internal resources. Concrete details: the issue arises from insufficient host restriction on mediaURL fetches, enabling potential a...

CVE-2025-6242 Vllm: server side request forgery (ssrf) in mediaconnector

A Server-Side Request Forgery SSRF vulnerability exists in the MediaConnector class within the vLLM project's multimodal feature set. The loadfromurl and loadfromurlasync methods fetch and process media from user-provided URLs without adequate restrictions on the target hosts. This allows an...

EUVD-2025-32903

LLaMA-Factory is a tuning library for large language models. Prior to version 0.9.4, a Server-Side Request Forgery SSRF vulnerability in the chat API allows any authenticated user to force the server to make arbitrary HTTP requests to internal and external networks. This can lead to the exposure ...

PT-2025-41177

Name of the Vulnerable Software and Affected Versions vLLM affected versions not specified Description An issue exists within the MediaConnector class in the vLLM project’s multimodal feature set. Specifically, the load from url and load from url async methods do not sufficiently restrict the...

EUVD-2024-0393

Malicious code in bioql PyPI...

LLaVul: a Multimodal LLM for Interpretable Vulnerability Reasoning about Source Code

Increasing complexity in software systems places a growing demand on reasoning tools that unlock vulnerabilities manifest in source code. Many current approaches focus on vulnerability analysis as a classifying task, oversimplifying the nuanced and context-dependent real-world scenarios. Even...

DMLDroid: Deep Multimodal Fusion Framework for Android Malware Detection with Resilience to Code Obfuscation and Adversarial Perturbations

In recent years, learning-based Android malware detection has seen significant advancements, with detectors generally falling into three categories: string-based, image-based, and graph-based approaches. While these methods have shown strong detection performance, they often struggle to sustain...

Aura-CAPTCHA: a Reinforcement Learning and GAN-Enhanced Multi-Modal CAPTCHA System

Aura-CAPTCHA was developed as a multi-modal CAPTCHA system to address vulnerabilities in traditional methods that are increasingly bypassed by AI technologies, such as Optical Character Recognition OCR and adversarial image processing. The design integrated Generative Adversarial Networks GANs fo...

MADPromptS: Unlocking Zero-Shot Morphing Attack Detection with Multiple Prompt Aggregation

Face Morphing Attack Detection MAD is a critical challenge in face recognition security, where attackers can fool systems by interpolating the identity information of two or more individuals into a single face image, resulting in samples that can be verified as belonging to multiple identities by...

CVE-2025-54624

Unexpected injection event vulnerability in the multimodalinput module. Impact: Successful exploitation of this vulnerability may affect availability...

CVE-2025-54624

Unexpected injection event vulnerability in the multimodalinput module. Impact: Successful exploitation of this vulnerability may affect availability...

From Learning to Unlearning: Biomedical Security Protection in Multimodal Large Language Models

The security of biomedical Multimodal Large Language Models MLLMs has attracted increasing attention. However, training samples easily contain private information and incorrect knowledge that are difficult to detect, potentially leading to privacy leakage or erroneous outputs after deployment. An...

Huawei HarmonyOS 安全漏洞

Huawei HarmonyOS is an operating system from Huawei China. It provides a full-scenario distributed operating system based on a microkernel. An unintended injection event vulnerability exists in the Huawei HarmonyOS multimodalinput module, which can be exploited by an attacker to cause availabilit...