35 matches found
anamorpher
Anamorpher Anamorpher named after anamorphosis is a tool for crafting and visualizing image scaling attacks against multi-modal AI systems. It provides a frontend interface and Python API for generating images that only reveal multi-modal prompt injections when downscaled. Refer to "Weaponizing...
EmailXpose
EmailXpose Specification AI-Powered Email Clarity HTML Mirror: https://roxanneardary.com/emailxpose-specification/ Specification Overview EmailXpose is an open source, modular AI email security and intelligence system designed to analyze email content, sender identity, links, attachments, images,...
MPIDetector: Detecting Multi-Modal Prompt Injection Via LLM-Based Reasoning
With the rapid integration of Multi-modal Large Language Models MLLMs into real-world applications, Prompt Injection PI has emerged as a critical security threat. Attackers can conceal malicious instructions within textual narratives or visual inputs to bypass safety alignment. Existing approache...
vLLM input validation vulnerability
Versions of vLLM prior to 0.31.0 have a vulnerability related to input validation errors. This vulnerability stems from using the multi-modal UUID provided by the client as a cache identifier without proper consistency checks when the cache is hit. This allows unauthenticated attackers to cause t...
Cost-Aware Hierarchical Multi-Agent Ransomware Detection and Family Attribution
Ransomware detection and family attribution require analysis of different modalities because it can use packing, obfuscation, process manipulation and runtime evasion techniques. However, conventional multimodal usually uses all available modalities for every sample resulting in unnecessary...
EmailXpose — Updated!
EmailXpose Specification AI-Powered Email Clarity HTML Mirror: https://roxanneardary.com/emailxpose-specification/ Specification Overview EmailXpose is an open source, modular AI email security and intelligence system designed to analyze email content, sender identity, links, attachments, images,...
CVE-2026-73560 vLLM: SSRF + arbitrary local file read in MiMoV2OmniMultiModalProcessor `_fetch_image` and audio loader bypass MediaConnector protections
vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the MiMoV2OmniMultiModalProcessor in vllm/transformersutils/processors/mimov2omni.py passes attacker-controlled image and audio strings through fetchimage, requests.get, and Image.open instead of MediaConnector,...
EmailXpose — Updated!
EmailXpose AI-Powered Email Clarity EmailXpose is an open source AI system that analyzes emails to detect phishing, spam, scams, and malware while also interpreting contextual meaning across text, images, and video. It goes beyond traditional security tools by combining threat intelligence,...
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...
PYSEC-2026-3046 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...
MAI-2024-0034
The Multi-Modal Linkage MML attack represents a sophisticated method to compromise Large Vision-Language Models VLMs by utilizing an "encryption-decryption" strategy across text and image modalities. This technique involves embedding malicious queries within images through methods such as word...
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...
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...
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...
CVE-2026-6587
A server-side request forgery (SSRF) vulnerability exists in vibrantlabsai RAGAS versions up to 0.4.3 (specifically prior to 0.4.4 ). The flaw is located in the Collections Module within the src/ragas/metrics/collections/multi_modal_faithfulness/util.py file, specifically affecting the _try_proce...
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...
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: Use of NullPointerException Catch to Detect 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...