paper-with-me

Papers

Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them

2021-07-24 · Florian Tramèr

Making classifiers robust to adversarial examples is hard. Thus, many defenses tackle the seemingly easier task of detecting perturbed inputs. We show a barrier towards this goal. We prove a general hardness reduction between detection and classification of adversarial examples: given a robust detector for attacks at distance {\epsilon} (in some metric), we can build a similarly robust (but inefficient) classifier for attacks at distance {\epsilon}/2. Our reduction is computationally inefficient, and thus cannot be used to build practical classifiers. Instead, it is a useful sanity check to test whether empirical detection results imply something much stronger than the authors presumably anticipated. To illustrate, we revisit 13 detector defenses. For 11/13 cases, we show that the claimed detection results would imply an inefficient classifier with robustness far beyond the state-of-the-art.

📄 PDF Abstract BibTeX arXiv:2107.11630

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them

2021-06-18 · ICML Workshop AML 2021 7 · Florian Tramer

Making classifiers robust to adversarial examples is hard. Thus, many defenses tackle the seemingly easier task of \emph{detecting} perturbed inputs. We show a barrier towards this goal. We prove a general \emph{hardne…

Training Ensembles to Detect Adversarial Examples

2017-12-11 · Alexander Bagnall, Razvan Bunescu, Gordon Stewart

We propose a new ensemble method for detecting and classifying adversarial examples generated by state-of-the-art attacks, including DeepFool and C&W. Our method works by training the members of an ensemble to have low c…

General Classification

Using Anomaly Feature Vectors for Detecting, Classifying and Warning of Outlier Adversarial Examples

2021-07-01 · ICML Workshop AML 2021 7 · Nelson Manohar-Alers, Ryan Feng, Sahib Singh, Jiguo Song 외

We present DeClaW, a system for detecting, classifying, and warning of adversarial inputs presented to a classification neural network. In contrast to current state-of-the-art methods that, given an input, detect whether…

Adversarial AttackAdversarial Attack Detection

AttackGNN: Red-Teaming GNNs in Hardware Security Using Reinforcement Learning

2024-02-21 · Vasudev Gohil, Satwik Patnaik, Dileep Kalathil, Jeyavijayan Rajendran

Machine learning has shown great promise in addressing several critical hardware security problems. In particular, researchers have developed novel graph neural network (GNN)-based techniques for detecting intellectual p…

Graph Neural NetworkRed Teamingreinforcement-learningReinforcement Learning+1

Evaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial Examples

2019-08-21 · Marcus Soll, Tobias Hinz, Sven Magg, Stefan Wermter

Adversarial examples are artificially modified input samples which lead to misclassifications, while not being detectable by humans. These adversarial examples are a challenge for many tasks such as image and text classi…

Adversarial TextClassificationGeneral Classificationimage-classification+3