PromptShield Home: Ambient Multimodal Prompt Injection Defense for Smart-Home Agents

Smart-home assistants increasingly use multimodal large language models MLLMs that perceive video and audio directly. This raises a safety question specific to the home: can the agent tell a genuine user command from ambient or externally-sourced content, television speech, on-screen text, or an...

Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment

Recent advancements in visual context compression enable MLLMs to process ultra-long contexts efficiently by rendering text into images. However, we identify a critical vulnerability inherent to this paradigm: lowering image resolution inadvertently catalyzes jailbreaking. Our experiments reveal...

CVE-2025-62372

vLLM is an inference and serving engine for large language models LLMs. From version 0.5.5 to before 0.11.1, users can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs with correct ndim but incorrect shape e.g. hidden dimension is wrong, regardless of whether...

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...

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...

LingoLoop Attack: Trapping MLLMs via Linguistic Context and State Entrapment into Endless Loops

Multimodal Large Language Models MLLMs have shown great promise but require substantial computational resources during inference. Attackers can exploit this by inducing excessive output, leading to resource exhaustion and service degradation. Prior energy-latency attacks aim to increase generatio...

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...