Article

Key-Activated Generative Security: Enforcing Access Control in Image Captioning Models

2025-09-11

Abstract excerpt

While the rapid progress of deep learning has endowed image captioning systems with remarkable generative power, it has simultaneously exposed them to unprecedented risks of intellectual property (IP) leakage and illicit replication. Conventional defense methods—most notably watermarking—have proven suitable for discriminative classifiers but remain inadequate for captioning networks, where outputs are structured,...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 820d91ec-61e1-5b47-91aa-be2ae4c8b46b
DOI: 10.20944/preprints202509.1001.v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Key-Activated Generative Security: Enforcing Access Control in Image Captioning ModelsDOI 10.20944/preprints202509.1001.v1Read

GReX-Bench: Benchmarking Generalization, Robustness, and Explainability in AI-Generated Image DetectionSemantic proximity Read

Beyond AI: Fooling DNN Model in Physical WorldSemantic proximity Read

Generation and Countermeasures of Adversarial Examples on Vision: A SurveySemantic proximity Read

QryptGen+: a quantum GAN-based high-security image encryption key generator with enhanced chaotic modelingSemantic proximity Read

Transient Deception: Recent Advances and Trends in Short-Lived Adversarial ExamplesSemantic proximity Read

Safety Evaluation of Google’s Gemini Nano Banana Image Model under Adversarial and Realistic Prompt ConditionsSemantic proximity Read

Image-embedded prompt injection vulnerability of vision-language models in dental radiology: a cross-vendor attack–defense evaluationSemantic proximity Read

Improving Transferability of Adversarial Examples with Mixed-Representation AttackSemantic proximity Read

Image Synthesis-based Backdoor Attack Approach in the Face Classification TaskSemantic proximity Read

Chained Dual-GAN: A Generalized Defense against Adversarial AttacksSemantic proximity Read

Benchmark Collapse in Text CAPTCHAs: Generator Heterogeneity, Cross-Generator Transfer, and Reliability-Aware Synthetic EvaluationSemantic proximity Read

Cycle-consistent Generative Adversarial Networks (CycleGANs) for the Non-Parallel Creation of Fake Voice MediaSemantic proximity Read