paper-with-me

홈 › Papers

Familiarity-Based Open-Set Recognition Under Adversarial Attacks

2023-11-08 · Philip Enevoldsen, Christian Gundersen, Nico Lang, Serge Belongie, Christian Igel

Open-set recognition (OSR), the identification of novel categories, can be a critical component when deploying classification models in real-world applications. Recent work has shown that familiarity-based scoring rules such as the Maximum Softmax Probability (MSP) or the Maximum Logit Score (MLS) are strong baselines when the closed-set accuracy is high. However, one of the potential weaknesses of familiarity-based OSR are adversarial attacks. Here, we study gradient-based adversarial attacks on familiarity scores for both types of attacks, False Familiarity and False Novelty attacks, and evaluate their effectiveness in informed and uninformed settings on TinyImageNet. Furthermore, we explore how novel and familiar samples react to adversarial attacks and formulate the adversarial reaction score as an alternative OSR scoring rule, which shows a high correlation with the MLS familiarity score.

📄 PDF Abstract BibTeX arXiv:2311.05006

Code (0)

등록된 구현이 없습니다.

Tasks

Open Set Learningscoring rule

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

The Familiarity Hypothesis: Explaining the Behavior of Deep Open Set Methods

2022-03-04 · Thomas G. Dietterich, Alexander Guyer

In many object recognition applications, the set of possible categories is an open set, and the deployed recognition system will encounter novel objects belonging to categories unseen during training. Detecting such "nov…

Anomaly DetectionObjectObject RecognitionOutlier Detection+1

Who is Real Bob? Adversarial Attacks on Speaker Recognition Systems

2019-11-03 · Guangke Chen, Sen Chen, Lingling Fan, Xiaoning Du 외

Speaker recognition (SR) is widely used in our daily life as a biometric authentication or identification mechanism. The popularity of SR brings in serious security concerns, as demonstrated by recent adversarial attacks…

Adversarial AttackSpeaker Recognitionspeech-recognitionSpeech Recognition

FACESEC: A Fine-grained Robustness Evaluation Framework for Face Recognition Systems

2021-04-08 · CVPR 2021 1 · Liang Tong, Zhengzhang Chen, Jingchao Ni, Wei Cheng 외

We present FACESEC, a framework for fine-grained robustness evaluation of face recognition systems. FACESEC evaluation is performed along four dimensions of adversarial modeling: the nature of perturbation (e.g., pixel-l…

Face Recognition

How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses

2023-05-18 · Joana C. Costa, Tiago Roxo, Hugo Proença, Pedro R. M. Inácio

Deep Learning is currently used to perform multiple tasks, such as object recognition, face recognition, and natural language processing. However, Deep Neural Networks (DNNs) are vulnerable to perturbations that alter th…

Face RecognitionMalware DetectionObject Recognition

Adversarial Light Projection Attacks on Face Recognition Systems: A Feasibility Study

2020-03-24 · Dinh-Luan Nguyen, Sunpreet S. Arora, Yuhang Wu, Hao Yang

Deep learning-based systems have been shown to be vulnerable to adversarial attacks in both digital and physical domains. While feasible, digital attacks have limited applicability in attacking deployed systems, includin…

Face Recognition