3 papers
cs.CV2026
AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models
Yuanmin Huang, Zhenfei Zhang, Mi Zhang +5
Text-to-image diffusion models have achieved high visual fidelity and broad adoption, but remain vulnerable to safety violations when adversaries exploit them to synthesize illicit…
cs.LG2026
Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework
Jiaqi Weng, Han Zheng, Hanyu Zhang +6
Sparse autoencoders (SAEs) enable interpretability research by decomposing entangled model activations into monosemantic features. However, under what circumstances SAEs derive mos…
cs.CV2025
A Single Neuron Works: Precise Concept Erasure in Text-to-Image Diffusion Models
Qinqin He, Jiaqi Weng, Jialing Tao +1
Text-to-image models exhibit remarkable capabilities in image generation. However, they also pose safety risks of generating harmful content. A key challenge of existing concept er…