paper-with-me

홈 › Papers

Exposing Fine-Grained Adversarial Vulnerability of Face Anti-Spoofing Models

2022-05-30 · Songlin Yang, Wei Wang, Chenye Xu, Ziwen He, Bo Peng, Jing Dong

Face anti-spoofing aims to discriminate the spoofing face images (e.g., printed photos) from live ones. However, adversarial examples greatly challenge its credibility, where adding some perturbation noise can easily change the predictions. Previous works conducted adversarial attack methods to evaluate the face anti-spoofing performance without any fine-grained analysis that which model architecture or auxiliary feature is vulnerable to the adversary. To handle this problem, we propose a novel framework to expose the fine-grained adversarial vulnerability of the face anti-spoofing models, which consists of a multitask module and a semantic feature augmentation (SFA) module. The multitask module can obtain different semantic features for further evaluation, but only attacking these semantic features fails to reflect the discrimination-related vulnerability. We then design the SFA module to introduce the data distribution prior for more discrimination-related gradient directions for generating adversarial examples. Comprehensive experiments show that SFA module increases the attack success rate by nearly 40$\%$ on average. We conduct this fine-grained adversarial analysis on different annotations, geometric maps, and backbone networks (e.g., Resnet network). These fine-grained adversarial examples can be used for selecting robust backbone networks and auxiliary features. They also can be used for adversarial training, which makes it practical to further improve the accuracy and robustness of the face anti-spoofing models.

📄 PDF Abstract BibTeX arXiv:2205.14851

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackAdversarial RobustnessFace Anti-Spoofing

Methods 이 논문이 사용한 방법론

Residual Connection 설명 없음
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
Kaiming Initialization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
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 $x$…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

GradingAttack: Exposing Security Vulnerabilities in LLM Based Educational Grading Agents

2026-02-01 · Xueyi Li, Zhuoneng Zhou, Zitao Liu, Yongdong Wu arxiv

Large language models (LLMs) are increasingly deployed as educational agents for automatic short answer grading (ASAG) in real-world educational environments, significantly boosting assessment efficiency and scalability.…

Adversarial Attack

When Lighting Deceives: Exposing Vision-Language Models' Illumination Vulnerability Through Illumination Transformation Attack

2025-03-10 · Hanqing Liu, Shouwei Ruan, Yao Huang, Shiji Zhao 외

Vision-Language Models (VLMs) have achieved remarkable success in various tasks, yet their robustness to real-world illumination variations remains largely unexplored. To bridge this gap, we propose \textbf{I}llumination…

Dual-Modality Multi-Stage Adversarial Safety Training: Robustifying Multimodal Web Agents Against Cross-Modal Attacks

2026-03-04 · Haoyu Liu, Dingcheng Li, Lukas Rutishauser, Zeyu Zheng arxiv

Multimodal web agents that process both screenshots and accessibility trees are increasingly deployed to interact with web interfaces, yet their dual-stream architecture opens an underexplored attack surface: an adversar…

Reinforcement Learning

HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectors

2026-01-09 · Jingxiao Yang, Ping He, Tianyu Du, Sun Bing 외 arxiv

Recent advances in software vulnerability detection have been driven by Language Model (LM)-based approaches. However, these models remain vulnerable to adversarial attacks that exploit lexical and syntax perturbations, …

Vulnerability DetectionCode Generation

AdversariaL attacK sAfety aLIgnment(ALKALI): Safeguarding LLMs through GRACE: Geometric Representation-Aware Contrastive Enhancement- Introducing Adversarial Vulnerability Quality Index (AVQI)

2025-06-10 · Danush Khanna, Krishna Kumar, Basab Ghosh, Vinija Jain 외

Adversarial threats against LLMs are escalating faster than current defenses can adapt. We expose a critical geometric blind spot in alignment: adversarial prompts exploit latent camouflage, embedding perilously close to…

Adversarial AttackSafety Alignment