Exposing Fine-Grained Adversarial Vulnerability of Face Anti-Spoofing Models
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackAdversarial RobustnessFace Anti-SpoofingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
GradingAttack: Exposing Security Vulnerabilities in LLM Based Educational Grading Agents
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 AttackWhen Lighting Deceives: Exposing Vision-Language Models' Illumination Vulnerability Through Illumination Transformation Attack
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
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 LearningHogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectors
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 GenerationAdversariaL attacK sAfety aLIgnment(ALKALI): Safeguarding LLMs through GRACE: Geometric Representation-Aware Contrastive Enhancement- Introducing Adversarial Vulnerability Quality Index (AVQI)
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