VulStyle: A Multi-Modal Pre-Training for Code Stylometry-Augmented Vulnerability Detection

We present VulStyle, a multi-modal software vulnerability detection model that jointly encodes function-level source code, non-terminal Abstract Syntax Tree AST structure, and code stylometry CStyle features. Prior work in code representation primarily leverages token-level models or full AST...

GHSA-95WW-475F-PR4F RAGAS has SSRF via Multi-Modal Faithfulness Collections Module

A security flaw has been discovered in vibrantlabsai RAGAS up to 0.4.3. The affected element is the function tryprocesslocalfile/tryprocessurl of the file src/ragas/metrics/collections/multimodalfaithfulness/util.py of the component Collections Module. Performing a manipulation of the argument...

RAGAS has SSRF via Multi-Modal Faithfulness Collections Module

A security flaw has been discovered in vibrantlabsai RAGAS up to 0.4.3. The affected element is the function tryprocesslocalfile/tryprocessurl of the file src/ragas/metrics/collections/multimodalfaithfulness/util.py of the component Collections Module. Performing a manipulation of the argument...

CVE-2026-6587

Vibrantlabsai RAGAS (up to 0.4.3) is affected in the Collections Module. The vulnerability lies in the function _try_process_local_file/_try_process_url (src/ragas/metrics/collections/multi_modal_faithfulness/util.py). Manipulating the argument retrieved_contexts can trigger a server-side request...

MemoPhishAgent: Memory-Augmented Multi-Modal LLM Agent for Phishing URL Detection

Traditional phishing website detection relies on static heuristics or reference lists, which lag behind rapidly evolving attacks. While recent systems incorporate large language models LLMs, they are still prompt-based, deterministic pipelines that underutilize reasoning capability. We present...

CVE-2025-15514

Ollama 0.11.5-rc0 through current version 0.13.5 contain a null pointer dereference vulnerability in the multi-modal model image processing functionality. When processing base64-encoded image data via the /api/chat endpoint, the application fails to validate that the decoded data represents valid...

CVE-2025-15514 Ollama Multi-Modal Model Image Processing NULL Pointer Dereference

Ollama 0.11.5-rc0 through current version 0.13.5 contain a null pointer dereference vulnerability in the multi-modal model image processing functionality. When processing base64-encoded image data via the /api/chat endpoint, the application fails to validate that the decoded data represents valid...

Trust in LLM-Controlled Robotics: A Survey of Security Threats, Defenses and Challenges

The integration of Large Language Models LLMs into robotics has revolutionized their ability to interpret complex human commands and execute sophisticated tasks. However, such paradigm shift introduces critical security vulnerabilities stemming from the ''embodiment gap'', a discord between the...

GRAPHTEXTACK: A Realistic Black-Box Node Injection Attack on LLM-Enhanced GNNs

Text-attributed graphs TAGs, which combine structural and textual node information, are ubiquitous across many domains. Recent work integrates Large Language Models LLMs with Graph Neural Networks GNNs to jointly model semantics and structure, resulting in more general and expressive models that...

Can Multi-Modal (Reasoning) LLMs Detect Document Manipulation?

Document fraud poses a significant threat to industries reliant on secure and verifiable documentation, necessitating robust detection mechanisms. This study investigates the efficacy of state-of-the-art multi-modal large language models LLMs-including OpenAI O1, OpenAI 4o, Gemini Flash thinking,...

Intrusion Detection in Heterogeneous Networks with Domain-Adaptive Multi-Modal Learning

Network Intrusion Detection Systems NIDS play a crucial role in safeguarding network infrastructure against cyberattacks. As the prevalence and sophistication of these attacks increase, machine learning and deep neural network approaches have emerged as effective tools for enhancing NIDS...

SAMEP: a Secure Protocol for Persistent Context Sharing across AI Agents

Current AI agent architectures suffer from ephemeral memory limitations, preventing effective collaboration and knowledge sharing across sessions and agent boundaries. We introduce SAMEP Secure Agent Memory Exchange Protocol, a novel framework that enables persistent, secure, and semantically...

QGuard:Question-Based Zero-Shot Guard for Multi-Modal LLM Safety

The recent advancements in Large Language ModelsLLMs have had a significant impact on a wide range of fields, from general domains to specialized areas. However, these advancements have also significantly increased the potential for malicious users to exploit harmful and jailbreak prompts for...

FAA Framework: a Large Language Model-Based Approach for Credit Card Fraud Investigations

The continuous growth of the e-commerce industry attracts fraudsters who exploit stolen credit card details. Companies often investigate suspicious transactions in order to retain customer trust and address gaps in their fraud detection systems. However, analysts are overwhelmed with an enormous...

NAP-Tuning: Neural Augmented Prompt Tuning for Adversarially Robust Vision-Language Models

Vision-Language Models VLMs such as CLIP have demonstrated remarkable capabilities in understanding relationships between visual and textual data through joint embedding spaces. Despite their effectiveness, these models remain vulnerable to adversarial attacks, particularly in the image modality,...

Multi-Modal Multi-Task Federated Foundation Models for Next-Generation Extended Reality Systems: Towards Privacy-Preserving Distributed Intelligence in AR/VR/MR

Extended reality XR systems, which consist of virtual reality VR, augmented reality AR, and mixed reality XR, offer a transformative interface for immersive, multi-modal, and embodied human-computer interaction. In this paper, we envision that multi-modal multi-task M3T federated foundation model...

BadReward: Clean-Label Poisoning of Reward Models in Text-To-Image RLHF

Reinforcement Learning from Human Feedback RLHF is crucial for aligning text-to-image T2I models with human preferences. However, RLHF's feedback mechanism also opens new pathways for adversaries. This paper demonstrates the feasibility of hijacking T2I models by poisoning a small fraction of...

ECG Identity Authentication in Open-Set with Multi-Model Pretraining and Self-Constraint Center and Irrelevant Sample Repulsion Learning

Electrocardiogram ECG signal exhibits inherent uniqueness, making it a promising biometric modality for identity authentication. As a result, ECG authentication has gained increasing attention in recent years. However, most existing methods focus primarily on improving authentication accuracy...

Indirect Instruction Injection in Multi-Modal LLMs

Interesting research: "Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs": Abstract: We demonstrate how images and sounds can be used for indirect prompt and instruction injection in multi-modal LLMs. An attacker generates an adversarial perturbation corresponding t...

Corporate Office and Kitchen Table: Securing the Future of Work, Part 1

The future of work is multi-modal, the future corporate office is a private coffee shop with great Wi-Fi, and the future of enterprise security is going to have to adapt rapidly. If there is a sliver of positivity that I can find in this devastating pandemic, it's that we are adapting and finding...