AI Paper Atlas

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

Evading Forensic Classifiers With Attribute-Conditioned Adversarial Faces

Fahad Shamshad, Koushik Srivatsan, Karthik Nandakumar

CVPR 2023 · Adversarial robustness and security › Attacks on text and graphs · approach: Diffusion-based adversarial purification · 9 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
Optimize noise together with latent codes rather than latent codes alone (ablation)Image-driven attack · Wang et al. forensic classifierASR: 89$\%$ -> 100$\%$Improved
Optimize noise together with latent codes rather than latent codes alone (ablation)Image-driven attack · Forensic classifiers, average FIDFID: 28.31 -> 26.44Improved
Optimize noise together with latent codes rather than latent codes alone (ablation)Text-guided attack · Wang et al. forensic classifierASR: 91$\%$ -> 100$\%$Improved
Optimize noise together with latent codes rather than latent codes alone (ablation)Text-guided attack · Forensic classifiers, average FIDFID: 34.73 -> 31.92Improved
Use meta-learning with alternating meta-train/meta-test classifier combinations instead of an ensembleText-guided attack · Held-out ResNet-18ASR: 11.0 -> 12.0Improved
Use meta-learning with alternating meta-train/meta-test classifier combinations instead of an ensembleText-guided attack · Held-out ResNet-50ASR: 32.0 -> 37.0Improved
Use meta-learning with alternating meta-train/meta-test classifier combinations instead of an ensembleText-guided attack · Held-out DenseNet-121ASR: 54.0 -> 64.0Improved
Use meta-learning with alternating meta-train/meta-test classifier combinations instead of an ensembleText-guided attack · Held-out EfficientNetASR: 46.0 -> 55.0Improved
Use meta-learning with alternating meta-train/meta-test classifier combinations instead of an ensembleText-guided attack · Held-out XceptionASR: 11.0 -> 14.0Improved
Replace reference-image inversion with direct adversarial optimization of attribute-specific latent codesImage-driven attack · Reference image attack, 100 samplesTime (sec): 105 -> 23Improved
Replace reference-image inversion with direct adversarial optimization of attribute-specific latent codesImage-driven attack · Reference image attack, 100 samplesASR: 100$\%$ -> 100$\%$No clear effect

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