Exploitation

2 items

RESEARCHarXiv CS.CL·4/13/2026

Re-Mask and Redirect: Exploiting Denoising Irreversibility in Diffusion Language Models

This paper reveals a critical vulnerability in diffusion-based language models (dLLMs) where their safety alignment, based on monotonic denoising schedules, can be easily bypassed. By re-masking refusal tokens and injecting an affirmative prefix, researchers achieved high attack success rates against prominent dLLMs, exposing a structural flaw.

Diffusion Models language models vulnerability Exploitation

DOCDEV.to AI·4/17/2026

Explaining Prompt Injection & Image Injection & How to counter them

This content explains what prompt and image injection are, identifying them as malicious AI exploitations. It details various countermeasures, such as treating user input as hostile and utilizing models to interpret image content for malicious intent.

Image Injection Exploitation prompt injection Mitigation