2 papers
cs.CR2026
MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models
Yingzi Ma, Zhengyue Zhao, Xiaogeng Liu +3
Diffusion large language models (dLLMs) generate text by iteratively denoising partially masked sequences under bidirectional context, exposing a safety surface distinct from autor…
cs.CR2025
From Pixels to Trajectory: Universal Adversarial Example Detection via Temporal Imprints
Yansong Gao, Huaibing Peng, Hua Ma +5
For the first time, we unveil discernible temporal (or historical) trajectory imprints resulting from adversarial example (AE) attacks. Standing in contrast to existing studies all…