Mitigating Evasion Attacks to Deep Neural Networks via Region-based Classification

By Xiaoyu Cao. 2018

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Stealing Hyperparameters in Machine Learning (2018, background): “Cao and Gong [8] found that adversarial examples, especially those generated by the attacks proposed by Carlini and Wagner, are close to the classiﬁcation boundary.”
Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers (2019, background): “Randomized smoothing was proposed by several works [23, 3] as a heuristic defense without proving any guarantees.”
ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models (2018, background): “Besides the above, many recent works have tackled security and privacy in machine learning from various perspectives [39], [16], [9], [37], [7], [27], [20], [45], [36], [21], [40], [29], [41], [20].”
Retrospective Adversarial Replay for Continual Learning (2022, unknown): “Training on such samples can help the model to learn about the boundaries between previous and current tasks and also retain the knowledge of previous tasks [7, 11, 23].”
Knowledge Distillation with Adversarial Samples Supporting Decision Boundary (2018, unknown): “Cao and Gong (2017) found that an adversarial sample was located near the decision boundary, and used this property to defense an adversarial attack.”
On Adaptive Attacks to Adversarial Example Defenses (2020, background): “An idea related to this term alone has previously been suggested as a defense (Cao & Gong, 2017) and was subsequently broken (He et al., 2018).”
Efficient Neural Network Robustness Certification with General Activation Functions (2018, background): “…required (soft-plus is demonstrated in [26]) Some recent works (such as robust optimization based adversarial training [30] or region-based classiﬁcation [31]) empirically exhibit strong robustness against several adversarial attacks, which is beyond the scope of provable robustness certiﬁcation.”