Prompt-driven Transferable Adversarial Attack on Person Re-Identification with Attribute-aware Textual Inversion
Person re-identification (re-id) models are vital in security surveillance systems, requiring transferable adversarial attacks to explore the vulnerabilities of them. Recently, vision-language models (VLM) based attacks have shown superior transferability by attacking generalized image and textual features of VLM, but they lack comprehensive feature disruption due to the overemphasis on discriminative semantics in integral representation. In this paper, we introduce the Attribute-aware Prompt Attack (AP-Attack), a novel method that leverages VLM's image-text alignment capability to explicitly disrupt fine-grained semantic features of pedestrian images by destroying attribute-specific textual embeddings. To obtain personalized textual descriptions for individual attributes, textual inversion networks are designed to map pedestrian images to pseudo tokens that represent semantic embeddings, trained in the contrastive learning manner with images and a predefined prompt template that explicitly describes the pedestrian attributes. Inverted benign and adversarial fine-grained textual semantics facilitate attacker in effectively conducting thorough disruptions, enhancing the transferability of adversarial examples. Extensive experiments show that AP-Attack achieves state-of-the-art transferability, significantly outperforming previous methods by 22.9% on mean Drop Rate in cross-model&dataset attack scenarios.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackAttributeContrastive LearningPerson Re-IdentificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks
Recent vision-language foundation models, such as CLIP, have demonstrated superior capabilities in learning representations that can be transferable across diverse range of downstream tasks and domains. With the emergenc…
Contrastive LearningPrompt LearningPersona-Conditioned Adversarial Prompting: Multi-Identity Red-Teaming for Adversarial Discovery and Mitigation
Automated red-teaming for LLMs often discovers narrow attack slices, missing diverse real-world threats, and yielding insufficient data for safety fine-tuning. We introduce Persona-Conditioned Adversarial Prompting (PCAP…
Transferable Adversarial Face Attack with Text Controlled Attribute
Traditional adversarial attacks typically produce adversarial examples under norm-constrained conditions, whereas unrestricted adversarial examples are free-form with semantically meaningful perturbations. Current unrest…
AttributeFace RecognitionTransferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking
The success of DNNs has driven the extensive applications of person re-identification (ReID) into a new era. However, whether ReID inherits the vulnerability of DNNs remains unexplored. To examine the robustness of ReID …
Adversarial AttackPerson Re-IdentificationTransferable Direct Prompt Injection via Activation-Guided MCMC Sampling
Direct Prompt Injection (DPI) attacks pose a critical security threat to Large Language Models (LLMs) due to their low barrier of execution and high potential damage. To address the impracticality of existing white-box/g…