AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Beyond Single-Point Perturbation: A Hierarchical, Manifold-Aware Approach to Diffusion Attacks

Zhijie Wang, Lin Wang, Zhenyu Wen, Cong Wang

AAAI 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Diffusion-based adversarial purification · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace CFG with prompt-free unconditional self-attention guidance (ablation)multi-step CFG attack · ImageNet-Compatible, Res-50FID: 69.7 -> 62.9Improved
add self-attention internal guidance (ablation)HAM · ImageNet-Compatible, Res-50transferabilityNo clear effect
add manifold-projected momentum (ablation)HAM · ImageNet-Compatible, Res-50ASRImproved
add dynamic step-wise manifold alignment (ablation)HAM · ImageNet-Compatible, Res-50ASR and FIDImproved
hierarchical multi-step attack vs DiffAttackHAM · ImageNet-Compatible, surrogate Inc-v3avg black-box ASR (%): 34.46 -> 56.12Improved
HAM vs DiffAttackHAM · ImageNet-Compatible, surrogate Res-50avg black-box ASR (%): 60.43 -> 66.63Improved
HAM vs ACAHAM · ImageNet-Compatible, surrogate Inc-v3avg black-box ASR (%): 62.34 vs 56.12Hurt
HAM vs DiffAttackHAM · ImageNet-Compatible, surrogate Inc-v3FID: 62.2 -> 64.7Hurt
HAM vs DiffAttackHAM · Defended models, Res-50avg ASR (%): 60.73 -> 67.11Improved
HAM vs ACAHAM · Computational costseconds per image: >200 -> 21.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy