paper-with-me

홈 › Papers

Uncovering Hidden Intentions: Exploring Prompt Recovery for Deeper Insights into Generated Texts

2024-06-22 · Louis Give, Timo Zaoral, Maria Antonietta Bruno

Today, the detection of AI-generated content is receiving more and more attention. Our idea is to go beyond detection and try to recover the prompt used to generate a text. This paper, to the best of our knowledge, introduces the first investigation in this particular domain without a closed set of tasks. Our goal is to study if this approach is promising. We experiment with zero-shot and few-shot in-context learning but also with LoRA fine-tuning. After that, we evaluate the benefits of using a semi-synthetic dataset. For this first study, we limit ourselves to text generated by a single model. The results show that it is possible to recover the original prompt with a reasonable degree of accuracy.

📄 PDF Abstract BibTeX arXiv:2406.15871

Code (0)

등록된 구현이 없습니다.

Tasks

In-Context Learning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Uncovering the Unseen: Discover Hidden Intentions by Micro-Behavior Graph Reasoning

2023-08-29 · Zhuo Zhou, Wenxuan Liu, Danni Xu, Zheng Wang 외

This paper introduces a new and challenging Hidden Intention Discovery (HID) task. Unlike existing intention recognition tasks, which are based on obvious visual representations to identify common intentions for normal b…

Intent Detection

Memory Self-Regeneration: Uncovering Hidden Knowledge in Unlearned Models

2025-09-26 · Agnieszka Polowczyk, Alicja Polowczyk, Joanna Waczyńska, Piotr Borycki 외 arxiv

The impressive capability of modern text-to-image models to generate realistic visuals has come with a serious drawback: they can be misused to create harmful, deceptive or unlawful content. This has accelerated the push…

Prompt Packer: Deceiving LLMs through Compositional Instruction with Hidden Attacks

2023-10-16 · Shuyu Jiang, Xingshu Chen, Rui Tang

Recently, Large language models (LLMs) with powerful general capabilities have been increasingly integrated into various Web applications, while undergoing alignment training to ensure that the generated content aligns w…

Ethics

Recovering the Lowest Layer of Deep Networks with High Threshold Activations

2019-03-21 · ICLR 2019 5 · Surbhi Goel, Rina Panigrahy

Giving provable guarantees for learning neural networks is a core challenge of machine learning theory. Most prior work gives parameter recovery guarantees for one hidden layer networks, however, the networks used in pra…

BIG-bench Machine LearningLearning TheoryVocal Bursts Intensity Prediction

Steganography Without Modification: Hidden Communication via LLM Seeds

2026-06-08 · Felix Mächtle, Jonas Sander, Sebastian Berndt, Ben Weimar 외 arxiv

We demonstrate that widely deployed Large Language Model (LLM) inference stacks harbor a steganographic channel that requires no modification to model weights, sampling code, or output distributions. The channel exploits…