Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents

[PDF] arxiv.org

Adversarial Hubness in Multi-Modal Retrieval

T Zhang, F Suya, R Jha, C Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
Hubness is a phenomenon in high-dimensional vector spaces where a single point from the
natural distribution is unusually close to many other points. This is a well-known problem in …
相关文章 所有 2 个版本
[PDF] arxiv.org

Unleashing worms and extracting data: Escalating the outcome of attacks against rag-based inference in scale and severity using jailbreaking

S Cohen, R Bitton, B Nassi - arXiv preprint arXiv:2409.08045, 2024 - arxiv.org
In this paper, we show that with the ability to jailbreak a GenAI model, attackers can escalate
the outcome of attacks against RAG-based GenAI-powered applications in severity and …
被引用次数：1 相关文章 所有 3 个版本
[PDF] arxiv.org

Adversarial Search Engine Optimization for Large Language Models

F Nestaas, E Debenedetti, F Tramèr - arXiv preprint arXiv:2406.18382, 2024 - arxiv.org
Large Language Models (LLMs) are increasingly used in applications where the model
selects from competing third-party content, such as in LLM-powered search engines or …
相关文章 所有 3 个版本