CVE-2025-54624

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

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...

SVC 2025: the First Multimodal Deception Detection Challenge

Deception detection is a critical task in real-world applications such as security screening, fraud prevention, and credibility assessment. While deep learning methods have shown promise in surpassing human-level performance, their effectiveness often depends on the availability of high-quality a...

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...

Invisible Injections: Exploiting Vision-Language Models through Steganographic Prompt Embedding

Vision-language models VLMs have revolutionized multimodal AI applications but introduce novel security vulnerabilities that remain largely unexplored. We present the first comprehensive study of steganographic prompt injection attacks against VLMs, where malicious instructions are invisibly...

Secure Tug-Of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security

The rapid advancement of multimodal large language models MLLMs has led to breakthroughs in various applications, yet their security remains a critical challenge. One pressing issue involves unsafe image-query pairs--jailbreak inputs specifically designed to bypass security constraints and elicit...

Scout: Leveraging Large Language Models for Rapid Digital Evidence Discovery

Recent technological advancements and the prevalence of technology in day to day activities have caused a major increase in the likelihood of the involvement of digital evidence in more and more legal investigations. Consumer-grade hardware is growing more powerful, with expanding memory and...

Unmasking Synthetic Realities in Generative AI: a Comprehensive Review of Adversarially Robust Deepfake Detection Systems

The rapid advancement of Generative Artificial Intelligence has fueled deepfake proliferation-synthetic media encompassing fully generated content and subtly edited authentic material-posing challenges to digital security, misinformation mitigation, and identity preservation. This systematic revi...

Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts across Modalities

Whitepaper called Bridging The Gap In Vision Language Models In Identifying Unsafe Concepts Across Modalities...

The Man behind the Sound: Demystifying Audio Private Attribute Profiling Via Multimodal Large Language Model Agents

Our research uncovers a novel privacy risk associated with multimodal large language models MLLMs: the ability to infer sensitive personal attributes from audio data -- a technique we term audio private attribute profiling. This capability poses a significant threat, as audio can be covertly...

PLA: Prompt Learning Attack against Text-To-Image Generative Models

Text-to-Image T2I models have gained widespread adoption across various applications. Despite the success, the potential misuse of T2I models poses significant risks of generating Not-Safe-For-Work NSFW content. To investigate the vulnerability of T2I models, this paper delves into adversarial...

CLIProv: a Contrastive Log-To-Intelligence Multimodal Approach for Threat Detection and Provenance Analysis

With the increasing complexity of cyberattacks, the proactive and forward-looking nature of threat intelligence has become more crucial for threat detection and provenance analysis. However, translating high-level attack patterns described in Tactics, Techniques, and Procedures TTP intelligence...

Evaluating the Critical Risks of Amazon'S Nova Premier under the Frontier Model Safety Framework

Nova Premier is Amazon's most capable multimodal foundation model and teacher for model distillation. It processes text, images, and video with a one-million-token context window, enabling analysis of large codebases, 400-page documents, and 90-minute videos in a single prompt. We present the fir...

Generative AI for Vulnerability Detection in 6G Wireless Networks: Advances, Case Study, and Future Directions

The rapid advancement of 6G wireless networks, IoT, and edge computing has significantly expanded the cyberattack surface, necessitating more intelligent and adaptive vulnerability detection mechanisms. Traditional security methods, while foundational, struggle with zero-day exploits, adversarial...

E-FreeM2: Efficient Training-Free Multi-Scale and Cross-Modal News Verification Via MLLMs

The rapid spread of misinformation in mobile and wireless networks presents critical security challenges. This study introduces a training-free, retrieval-based multimodal fact verification system that leverages pretrained vision-language models and large language models for credibility assessmen...

llama.cpp 安全漏洞

llama.cpp is a multimodal model by the individual developer Georgi Gerganov. A security vulnerability exists in versions of llama.cpp prior to b5721, which stems from the presence of signed and unsigned integer overflows in the tokenizer implementation, which could lead to a heap overflow...

Pushing the Limits of Safety: a Technical Report on the ATLAS Challenge 2025

Multimodal Large Language Models MLLMs have enabled transformative advancements across diverse applications but remain susceptible to safety threats, especially jailbreak attacks that induce harmful outputs. To systematically evaluate and improve their safety, we organized the Adversarial Testing...

DinoCompanion: an Attachment-Theory Informed Multimodal Robot for Emotionally Responsive Child-AI Interaction

Children's emotional development fundamentally relies on secure attachment relationships, yet current AI companions lack the theoretical foundation to provide developmentally appropriate emotional support. We introduce DinoCompanion, the first attachment-theory-grounded multimodal robot for...

Investigating Vulnerabilities and Defenses against Audio-Visual Attacks: a Comprehensive Survey Emphasizing Multimodal Models

Multimodal large language models MLLMs, which bridge the gap between audio-visual and natural language processing, achieve state-of-the-art performance on several audio-visual tasks. Despite the superior performance of MLLMs, the scarcity of high-quality audio-visual training data and computation...

InverTune: Removing Backdoors from Multimodal Contrastive Learning Models Via Trigger Inversion and Activation Tuning

Multimodal contrastive learning models like CLIP have demonstrated remarkable vision-language alignment capabilities, yet their vulnerability to backdoor attacks poses critical security risks. Attackers can implant latent triggers that persist through downstream tasks, enabling malicious control ...