Command Palette
Search for a command to run...

Researchers Build Task Vector Backdoor in AI Models Tested on Llama, Mistral and DeepSeek

aiai-governanceai-legal-safetyai-modelingai-research-evalstechcybersecurity 1 posts · 1 accounts

Researchers build a poisoned AI skill file that embeds a hidden backdoor using a technique called task arithmetic. The method uses a small task vector file that lets developers add or subtract capabilities from a model without retraining, triggering the backdoor whether the skill is installed or removed.

The testing covered image models and large language models, including Llama, Mistral, Phi-4, and DeepSeek. Defenses currently in use failed to detect the file. The finding highlights a supply-chain risk for public model hubs, where downloading a single skill package could introduce malware into an organization’s AI infrastructure.

From the sources (1 posts)

@intcyberdigest

‼️ Researchers built BadTV, a poisoned "skill file" for AI models that hides a backdoor firing whether you install a skill or strip one away. Normally, teaching an AI model a new skill means expensive retraining. A shortcut called "task ar

Preview built on a synthetic news corpus (16 weeks, Apr–Jul 2026). Impact calls are model reads, not price data.

About Archive