Research map / Adversarial robustness and security / Attacks on text and graphs
On Adaptive Attacks to Adversarial Example Defenses
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| replace defense evaluation with adaptive PGD using smoothed gradients (k-WTA) | k-WTA ResNet-18 · CIFAR-10 | robust accuracy: 50.0 -> 0.16 | Hurt |
| increase PGD step size by 3x | Ensemble Diversity defense · CIFAR-10 | robust accuracy: 48\% to 26\% | Hurt |
| increase PGD iterations to 250 | Ensemble Diversity defense · CIFAR-10 | robust accuracy: 20\% while 250 iterations reduced the accuracy to 10 | Hurt |
| repeat attack 3 times per example | Ensemble Diversity defense · CIFAR-10 | robust accuracy | Hurt |
| divide logits by a large constant before attack | Rethinking Softmax CE defense · CIFAR-10 | robust accuracy: 24\%$ to $18 | Hurt |
| remove numerically unstable sigmoid/log ops and use hinge loss | ECC defense · CIFAR-10 | robust accuracy | Hurt |
| use simple consistent loss with 100 PGD iterations | EMPIR defense · CIFAR-10 | robust accuracy | Hurt |
Closest papers by meaning
- Automated Discovery of Adaptive Attacks on Adversarial Defenses (NeurIPS 2021 · similarity 0.93)
- Are adversarial examples inevitable? (ICLR 2019 · similarity 0.90)
- Are Adversarial Examples Created Equal? A Learnable Weighted Minimax Risk for Robustness under Non-uniform Attacks (AAAI 2021 · similarity 0.89)
- Adversarial Risk and the Dangers of Evaluating Against Weak Attacks (ICML 2018 · similarity 0.89)
- Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack (CVPR 2022 · similarity 0.88)
- Constructing Semantics-Aware Adversarial Examples with a Probabilistic Perspective (NeurIPS 2024 · similarity 0.85)
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.