Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)
-
Updated
Dec 16, 2022 - Python
Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation (NeurIPS 2022)
The official code of IEEE S&P 2024 paper "Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability". We study how to train surrogates model for boosting transfer attack.
KENKU: Towards Efficient and Stealthy Black-box Adversarial Attacks against ASR Systems
[DSN 2024] Toward Evaluating Robustness of Reinforcement Learning with Adversarial Policy
PyTorch implementation of “Conditional Adversarial Camera Model Anonymization” (ECCV 2020 Advances in Image Manipulation Workshop)
End-to-end PE malware detection with XGBoost and MalConv2. Adversarial robustness evaluation via GAMMA attack, SHAP interpretability, and multi-model Pareto comparison.
《拓扑生成范式:算力革命与黑箱破解》针对现有AI拟合路线算力爆炸、黑箱不可解释、沙箱越狱问题,提出低维骨架+表层填充的范式迁移,可大幅降低算力,实现生成过程可追溯可控。Topology‑Generating Paradigm: skeleton‑fill two‑layer forward‑generation framework. Solve AI black‑box, jailbreak and computing‑power explosion problems. Reduce computational cost by orders of magnitude, interpretable & traceable generation.
To associate your repository with the black-box-attack topic, visit your repo's landing page and select "manage topics."