Building Trustworthy Multimodal AI: a Review of Fairness, Transparency, and Ethics in Vision-Language Tasks

Objective: This review explores the trustworthiness of multimodal artificial intelligence AI systems, specifically focusing on vision-language tasks. It addresses critical challenges related to fairness, transparency, and ethical implications in these systems, providing a comparative analysis of...

CVE-2025-46560 vLLM phi4mm: Quadratic Time Complexity in Input Token Processing​ leads to denial of service

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens...

CVE-2025-46560 vLLM phi4mm: Quadratic Time Complexity in Input Token Processing​ leads to denial of service

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens...

GHSA-VC6M-HM49-G9QG vLLM: Quadratic Time Complexity in Input Token Processing​ leads to denial of service

Summary A critical performance vulnerability has been identified in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens e.g., , with repeated tokens based on precomputed lengths. Due to ​​inefficient list concatenation operations​​, the...

AGATE: Stealthy Black-Box Watermarking for Multimodal Model Copyright Protection

Recent advancement in large-scale Artificial Intelligence AI models offering multimodal services have become foundational in AI systems, making them prime targets for model theft. Existing methods select Out-of-Distribution OoD data as backdoor watermarks and retrain the original model for...

T2VShield: Model-Agnostic Jailbreak Defense for Text-To-Video Models

The rapid development of generative artificial intelligence has made text to video models essential for building future multimodal world simulators. However, these models remain vulnerable to jailbreak attacks, where specially crafted prompts bypass safety mechanisms and lead to the generation of...

Semantic-Aware Contrastive Fine-Tuning: Boosting Multimodal Malware Classification with Discriminative Embeddings

The rapid evolution of malware variants requires robust classification methods to enhance cybersecurity. While Large Language Models LLMs offer potential for generating malware descriptions to aid family classification, their utility is limited by semantic embedding overlaps and misalignment with...

IoT-AMLHP: Aligned Multimodal Learning of Header-Payload Representations for Resource-Efficient Malicious IoT Traffic Classification

Traffic classification is crucial for securing Internet of Things IoT networks. Deep learning-based methods can autonomously extract latent patterns from massive network traffic, demonstrating significant potential for IoT traffic classification tasks. However, the limited computational and spati...

On the Feasibility of Using MultiModal LLMs to Execute AR Social Engineering Attacks

Augmented Reality AR and Multimodal Large Language Models LLMs are rapidly evolving, providing unprecedented capabilities for human-computer interaction. However, their integration introduces a new attack surface for social engineering. In this paper, we systematically investigate the feasibility...

The vulnerability of the check_access() function in the system for launching and managing large language multimodal systems (LoLLMS) allows a perpetrator to gain access to read, modify, or delete data, or to cause service failures.

The vulnerability of the checkaccess function in the system for launching and managing large language multimodal systems LoLLMS is related to deficiencies in the authentication process. Exploiting this vulnerability could allow an attacker to gain read, modify, or delete access to data, or to cau...

Introducing Spring AI Amazon Bedrock Nova Integration via Converse API

The Amazon Bedrock Nova models represent a new generation of foundation models supporting a broad range of use cases, from text and image understanding to video-to-text analysis. With the Spring AI Bedrock Converse API integration, developers can seamlessly connect to these advanced Nova models a...

Audio Multimodality: Expanding AI Interaction with Spring AI and OpenAI

This blog post is co-authored by our great contributor Thomas Vitale. OpenAI provides specialized models for speech-to-text and text-to-speech conversion, recognized for their performance and cost-efficiency. Spring AI integrates these capabilities via Voice-to-Text and Text-to-Speech TTS. The ne...

LoLLMs 访问控制错误漏洞

LoLLMs is a Web UI for a large language multimodal system by the individual developer Saifeddine ALOUI. An access control error vulnerability exists in LoLLMs versions prior to v10 that stems from the presence of a CORS configuration error that can be exploited by an attacker to steal sensitive...

LoLLMs 安全漏洞

LoLLMs is a Web UI for a large language multimodal system by the individual developer Saifeddine ALOUI. A security vulnerability exists in LoLLMs that stems from improper parameter cleanup, resulting in a path traversal vulnerability that allows an attacker to read any file on the victim's comput...

Taxonomy of Generative AI Misuse

Interesting paper: "Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data”: Generative, multimodal artificial intelligence GenAI offers transformative potential across industries, but its misuse poses significant risks. Prior research has shed light on the potential of...

llama.cpp 安全漏洞

llama.cpp is a multimodal model. llama.cpp suffers from a remote code execution vulnerability that originates in the data pointer in the rpctensor structure, which can be exploited by an attacker to cause an arbitrary address to be read...

This Week in Spring - July 29th, 2024

Hi Spring fans! Welcome to another installment of This Week in Spring! It's July 29th, 2024! I can hardly believe it! We're less than a month away from SpringOne 2024! Have you registered for either in-person attendance or the free livestreams yet? As always, we've got a ton of stuff to cover so...

LoLLMs Code Injection Vulnerability

LoLLMs is a Web UI for a large language multimodal system by the individual developer Saifeddine ALOUI. A code injection vulnerability exists in LoLLMs version 5.9.0, which stems from the presence of a remote code execution vulnerability that allows an attacker to inject arbitrary commands via th...

LoLLMs Security Vulnerabilities

LoLLMs is a Web UI for a large language multimodal system by the individual developer Saifeddine ALOUI. A security vulnerability exists in LoLLMs that stems from a path traversal vulnerability in the application...

LoLLMs Security Vulnerabilities

LoLLMs is a Web UI for a large language multimodal system by the individual developer Saifeddine ALOUI. A security vulnerability exists in LoLLMs that stems from a path traversal vulnerability in the application...