paper-with-me

Papers

Identifying Adversarially Attackable and Robust Samples

2023-01-30 · Vyas Raina, Mark Gales

Adversarial attacks insert small, imperceptible perturbations to input samples that cause large, undesired changes to the output of deep learning models. Despite extensive research on generating adversarial attacks and building defense systems, there has been limited research on understanding adversarial attacks from an input-data perspective. This work introduces the notion of sample attackability, where we aim to identify samples that are most susceptible to adversarial attacks (attackable samples) and conversely also identify the least susceptible samples (robust samples). We propose a deep-learning-based detector to identify the adversarially attackable and robust samples in an unseen dataset for an unseen target model. Experiments on standard image classification datasets enables us to assess the portability of the deep attackability detector across a range of architectures. We find that the deep attackability detector performs better than simple model uncertainty-based measures for identifying the attackable/robust samples. This suggests that uncertainty is an inadequate proxy for measuring sample distance to a decision boundary. In addition to better understanding adversarial attack theory, it is found that the ability to identify the adversarially attackable and robust samples has implications for improving the efficiency of sample-selection tasks.

📄 PDF Abstract BibTeX arXiv:2301.12896

Code (1)

rainavyas/img_attackability 공식 구현 pytorch

Tasks

Active LearningAdversarial Attackimage-classificationImage Classification

Similar Papers 제목 키워드 기반

Sample Attackability in Natural Language Adversarial Attacks

2023-06-21 · Vyas Raina, Mark Gales

Adversarial attack research in natural language processing (NLP) has made significant progress in designing powerful attack methods and defence approaches. However, few efforts have sought to identify which source sample…

Adversarial Attack

Robust learning under clean-label attack

2021-03-01 · Avrim Blum, Steve Hanneke, Jian Qian, Han Shao

We study the problem of robust learning under clean-label data-poisoning attacks, where the attacker injects (an arbitrary set of) correctly-labeled examples to the training set to fool the algorithm into making mistakes…

Data PoisoningPAC learning

Detecting Attackable Sentences in Arguments

2020-10-06 · EMNLP 2020 11 · Yohan Jo, Seojin Bang, Emaad Manzoor, Eduard Hovy 외

Finding attackable sentences in an argument is the first step toward successful refutation in argumentation. We present a first large-scale analysis of sentence attackability in online arguments. We analyze driving reaso…

BIG-bench Machine LearningSentence

When Are Linear Stochastic Bandits Attackable?

2021-10-18 · Huazheng Wang, Haifeng Xu, Hongning Wang

We study adversarial attacks on linear stochastic bandits: by manipulating the rewards, an adversary aims to control the behaviour of the bandit algorithm. Perhaps surprisingly, we first show that some attack goals can n…

Decision MakingRecommendation Systems

Guided Interpolation for Adversarial Training

2021-02-15 · Chen Chen, Jingfeng Zhang, Xilie Xu, Tianlei Hu 외

To enhance adversarial robustness, adversarial training learns deep neural networks on the adversarial variants generated by their natural data. However, as the training progresses, the training data becomes less and les…

Adversarial Robustness