Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 9 of 9 for “"model stealing"”.
-
ENHANCING PRIVACY WHILE REVEALING VULNERABILITIES: STRATEGIES FOR ADAPTATION, OPTIMIZATION, AND MODEL EXTRACTION
… for secure knowledge transfer, enhancing the model performance of tiny models, and executing model stealing attacks via diversified prompts. The overarching goal is to enhance the performance, scalability, and security of AI models across various applications. The first research focus is on …
-
Privacy Attacks and Defenses under Security Threats in Machine Learning
… performance. However, machine learning models exhibit some vulnerabilities against threats in the real world, including privacy risks and security concerns. In terms of privacy risks, malicious users can steal the private information of other users or model owners, including recovering …
-
Rethinking adversarial robustness in the context of the right to be forgotten
… data, they overlook investigating the unlearned models' susceptibility to adversarial attacks and security breaches. In this work, we uncover a novel security vulnerability of machine unlearning based on the insight that adversarial vulnerabilities can be bolstered, especially for adversarially …
-
Machine Learning in Industry: Applications and Security Challenges
… as data poisoning attacks, adversarial attacks, model stealing attacks, and membership inference attacks. To address these concerns, we investigate the reliability and robustness of the crack detection system. Specifically, we design a backdoor attack, a type of data poisoning attack that injects …
-
Ataques adversarios en redes neuronales: análisis de transferabilidad y generación de imágenes adversarias mediante modelos difusos
… y predicción de incidentes a medida que los modelos han ido mejorando y la potencia de sistemas de cómputo han permitido un volumen mayor de datos para el entrenamiento. Actualmente la inteligencia artificial está logrando resultados sorprendentes, podemos ver como ChatGPT es capaz de generar …
-
Toward managing catastrophic AI risks
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms
-
In the Shadow of Prompts: Adversarial Attacks and Model Cloning in Large Language Models
Large-language models (LLMs) already power mission critical tasks such as command-and-control chat, satellite ground-station automation, military analytics, and cyber-defense. Since most of these services are offered through application programming interfaces (APIs) that still expose full or top-k …
-
Krádež modelů strojového učení pomocí dotazování
Tato práce se zabývá útoky zaměřenými na extrakci modelů v rámci služeb strojového učení (MLaaS), které jsou přístupné přes black-box prostředí. Teoretická část práce shrnuje taxonomie extrakce a poskytuje přehled praktických obranných metod, včetně monitorování dotazů. Praktická část se zaměřuje …