Connected & Protected
24/7 Support
📄
1 Article

Artificial Intelligence, Cyberattacks, Generative AI, Security Articles & Insights

Explore our collection of artificial intelligence, cyberattacks, generative ai, security articles, written by industry professionals with hands-on experience.

All Topics
Technology
Artificial intelligence
Management
Networking
Artificial Intelligence, Data Center, Emerging Technology, Google, Vendors and Providers
News
Bugs
Android, Google, Messaging Apps, Productivity Software
Apple, Endpoint Protection, iOS, MacOS, Mobile Security, Security
Small Business Operations
Franchise
Product
Artificial Intelligence, Cybercrime, Fraud, Security
Artificial Intelligence, Cyberattacks, Cybercrime, Industry, Markets, Retail Industry, Security
Global Affairs
Company
Startup
The Download
Gear
Business
AI & Machine Learning
Hardware & Infrastructure
Windows 11
Asus
Software Apps
Cybersecurity
Articles
Software Development
AI
Microsoft
BCDR
Security, Vulnerabilities
Cybercrime, Malware, Ransomware, Security
Network Security, Security, Vulnerabilities
Communications Security, Email Security, Network Security, Security, Vulnerabilities, Zero-Day Vulnerabilities
Artificial Intelligence, Cyberattacks, Generative AI, Security
The Good, the Bad and the Ugly
OpenAI Academy
Business Technology
Data & Analytics
Security
Phishing, Security, Social Engineering
Cloud Computing
Cybercrime, Security
Cyberattacks, Cybercrime, Healthcare Industry, Security
Research
Endpoint Protection, Malware, Mobile Security, Security
Security, Vulnerabilities, Zero-Day Vulnerabilities
Generative AI
PC Gaming
Engineering
Microsoft Copilot
Biotechnology and health
Artificial Intelligence, Cybercrime, Malware, Security
Network Security, Security, VPN, Vulnerabilities, Zero-Day Vulnerabilities
Politics
Driving
Communications Security, Email Security, Network Security, Security, Vulnerabilities
IT Leadership, IT Management, IT Skills and Training, Security, Security Operations Center
Artificial Intelligence, Data Privacy, Privacy, Security
Phishing, Security, Vulnerabilities
Artificial Intelligence, Data and Information Security, Security, Threat and Vulnerability Management
Dell
Uncategorized
Channel Partners
Science
Cameras
Artificial Intelligence
Analytics and AI
Culture
Tech
Data Center
Cloud
Featured
Business / Artificial Intelligence
How-To
Corporate
Education
General
Cloud Services
New image-based prompt injection attack targets multimodal AI models
•Artificial Intelligence, Cyberattacks, Generative AI, Security

New image-based prompt injection attack targets multimodal AI models

Security researchers have developed a new image-based prompt injection attack that can manipulate how multimodal AI systems interpret user instructions without modifying the original text prompt, potentially expanding security risks for AI agents and vision-language systems. In a research paper published this week, researchers from Xidian University described a technique called “CrossMPI,” which uses nearly imperceptible image perturbations to alter how large vision-language models (LVLMs) process both visual and textual inputs. “CrossMPI can steer the model’s interpretation of both textual and visual inputs via image-only prompt injection,” the researchers wrote in the paper. Unlike traditional prompt injection attacks, which typically rely on malicious text instructions embedded in prompts or webpages, the new technique attempts to change how the model interprets a benign user request by manipulating images alone. “The perturbed image can manipulate the model’s understanding of the user’s instruction,” the paper said. In one example described in the paper, researchers subtly modified an image of an airplane using nearly imperceptible pixel-level perturbations invisible to human users. When a multimodal AI system was then asked whether the airplane belonged to Air Canada, the manipulated image caused the model to incorrectly identify the object as “a mobile phone,” illustrating how the attack could distort both visual understanding and interpretation of the user’s task. The findings add to growing concerns around multimodal AI security as enterprises increasingly deploy AI copilots, autonomous agents, document-processing assistants, and vision-enabled workflows that combine image and text reasoning. Apeksha Kaushik, senior principal analyst at Gartner, said the risks could grow rapidly as enterprises adopt more multimodal AI systems. “By 2030, 80% of enterprise software and applications will be multimodal, up from 1% in 2024,” Kaushik said. Attack targets multimodal reasoning layers Prompt injection has emerged as one of the most closely watched risks in generative AI systems, particularly as organizations adopt AI agents capable of interacting with enterprise applications, websites, documents, and external tools. Most existing prompt injection attacks rely on malicious text embedded in prompts, webpages, or hidden instructions. Some multimodal attacks have also attempted to manipulate AI behavior using images containing visible or hidden text instructions. The researchers argued their approach differs because it attempts to alter how the model interprets the original task itself through image perturbations alone. By contrast with earlier methods, the researchers noted that CrossMPI uses image modifications to “change the model’s interpretation of both the visual and textual prompts.” The paper said the attack specifically targets the “hidden state space of LVLMs” — the stage where models combine textual instructions and visual evidence into internal representations before generating outputs. According to the paper, the most effective attack layers were not the final output layers traditionally targeted in adversarial AI attacks, but intermediate layers where visual and textual information are fused together. Researchers claim strong black-box transferability The researchers evaluated the technique against multiple open-source LVLMs, including MiniGPT4, BLIP-2, InstructBLIP, BLIVA, and Qwen2.5-VL, the paper added. According to the paper, the attack achieved an average success rate of 66.36% across tested models, outperforming prior baseline attacks by roughly 41 percentage points. The researchers also said the technique demonstrated “strong transferability in black-box settings,” meaning the attacks remained effective even without direct access to a target model’s parameters or architecture. The paper further claimed the perturbations remained visually stealthy while maintaining effectiveness across multiple LVLM architectures. No effective defense The researchers evaluated several defense mechanisms designed to neutralize hidden image manipulations, including random resizing, image rotation, JPEG compression, and inference-level safeguards such as SmoothVLM, a specialized defense framework designed to protect Vision-Language Models (VLMs) from patched visual prompt injections, and DPS, which guides models using partial image views. According to the paper, SmoothVLM proved the most effective, reducing attack success rates to below 5% in several scenarios, while JPEG compression also weakened the attacks by suppressing high-frequency image artifacts. However, the researchers said none of the tested defenses completely eliminated the attacks, suggesting stronger multimodal AI security protections may still be needed. Enterprise AI deployments may widen exposure The research arrives as enterprises rapidly expand deployments of multimodal AI systems capable of processing screenshots, PDFs, dashboards, forms, video streams, and enterprise documents alongside natural language prompts. The researchers noted that adversarial examples generated using the technique could potentially “mislead VLM-based web agents” and “disrupt real-world object detectors.” “Even if textual inputs are sanitized, manipulated images can still subvert the model’s outputs or actions,” Kaushik said. She said organizations that use multimodal AI for document processing, customer interactions, content moderation, and autonomous systems may face increasing exposure to adversarial image manipulation and prompt injection attacks. “Security controls designed for unimodal systems are insufficient,” Kaushik said. The researchers acknowledged that the work was conducted in controlled research settings using open-source models and did not describe observed exploitation in real-world enterprise environments.

#Artificial Intelligence, Cyberattacks, Generative AI, Security
#image-based prompt injection
#multimodal AI security
#CrossMPI technique
#AI model vulnerabilities
+4 more
Microsoft disrupts malware code-signing service used by ransomware gangs | CSO Online
Content Author

Stay Updated with AI & IT Trends

Join over 1,000 IT professionals receiving weekly insights on artificial intelligence, cybersecurity, and emerging technologies.

No spam, unsubscribe anytime. Read by IT leaders at Fortune 500 companies.

Need Expert Help?

Our certified professionals can help you implement the solutions discussed in these articles.