conftrace_

attention manipulation

7 papers

Explore in graph

Co-occurring keywords · papers mentioning both

adversarial attack (3) image editing (2) feature replacement (1) trojan attack (1) trojan behavior (1) poisoning rate (1) consistent editing (1) attention layer (1) harmless generation (1) multimodal diffusion transformer (1)

Papers

Manipulating the Mind’s Eye: A-SAGE, the Attention-Based Attack on ViT Explainability AAAI 2026 Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment EMNLP 2025 Edicho: Consistent Image Editing in the Wild ICCV 2025 MaskCD: Mitigating LVLM Hallucinations by Image Head Masked Contrastive Decoding EMNLP 2025 QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing ICCV 2025 Attention-Enhancing Backdoor Attacks Against BERT-based Models EMNLP 2023 Self-Detoxifying Language Models via Toxification Reversal EMNLP 2023