Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution
Fuente:
arXiv
Saved in:
| Main Authors: | Alizadeh, Meysam, Samei, Zeynab, Stetsenko, Daria, Gilardi, Fabrizio |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
Verifiable Dropout: Turning Randomness into a Verifiable Claim
by: Lee, Kichang, et al.
Published: (2025)
by: Lee, Kichang, et al.
Published: (2025)
From Benchmarks to Business Impact: Deploying IBM Generalist Agent in Enterprise Production
by: Shlomov, Segev, et al.
Published: (2025)
by: Shlomov, Segev, et al.
Published: (2025)
When Audio Generators Become Good Listeners: Generative Features for Understanding Tasks
by: Xie, Zeyu, et al.
Published: (2025)
by: Xie, Zeyu, et al.
Published: (2025)
Any four real numbers are on all fours with analogy
by: Lepage, Yves, et al.
Published: (2024)
by: Lepage, Yves, et al.
Published: (2024)
Contemporary Agent Technology: LLM-Driven Advancements vs Classic Multi-Agent Systems
by: Bădică, Costin, et al.
Published: (2025)
by: Bădică, Costin, et al.
Published: (2025)
SemanticVocoder: Bridging Audio Generation and Audio Understanding via Semantic Latents
by: Xie, Zeyu, et al.
Published: (2026)
by: Xie, Zeyu, et al.
Published: (2026)
RMFlow: Refined Mean Flow by a Noise-Injection Step for Multimodal Generation
by: Huang, Yuhao, et al.
Published: (2026)
by: Huang, Yuhao, et al.
Published: (2026)
CAST-TTS: A Simple Cross-Attention Framework for Unified Timbre Control in TTS
by: Zheng, Zihao, et al.
Published: (2026)
by: Zheng, Zihao, et al.
Published: (2026)
Self-Composing Neural Operators with Depth and Accuracy Scaling via Adaptive Train-and-Unroll Approach
by: He, Juncai, et al.
Published: (2025)
by: He, Juncai, et al.
Published: (2025)
GraphCNNpred: A stock market indices prediction using a Graph based deep learning system
by: Jin, Yuhui
Published: (2024)
by: Jin, Yuhui
Published: (2024)
On the Robustness of Decision-Focused Learning
by: Farhat, Yehya
Published: (2023)
by: Farhat, Yehya
Published: (2023)
Big Data Intelligence Using Distributed Deep Neural Networks
by: Ongati, Felix, et al.
Published: (2019)
by: Ongati, Felix, et al.
Published: (2019)
Detection of Chagas Disease from the ECG: The George B. Moody PhysioNet Challenge 2025
by: Reyna, Matthew A., et al.
Published: (2025)
by: Reyna, Matthew A., et al.
Published: (2025)
Distributional Drift Adaptation with Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecasting
by: He, Hui, et al.
Published: (2022)
by: He, Hui, et al.
Published: (2022)
ViMo: Generating Motions from Casual Videos
by: Qiu, Liangdong, et al.
Published: (2024)
by: Qiu, Liangdong, et al.
Published: (2024)
STAR: Speech-to-Audio Generation via Representation Learning
by: Xie, Zeyu, et al.
Published: (2025)
by: Xie, Zeyu, et al.
Published: (2025)
Moving Object Proposals with Deep Learned Optical Flow for Video Object Segmentation
by: Shi, Ge, et al.
Published: (2024)
by: Shi, Ge, et al.
Published: (2024)
Exploring ChatGPT and its Impact on Society
by: Haque, Md. Asraful, et al.
Published: (2024)
by: Haque, Md. Asraful, et al.
Published: (2024)
FakeSound2: A Benchmark for Explainable and Generalizable Deepfake Sound Detection
by: Xie, Zeyu, et al.
Published: (2025)
by: Xie, Zeyu, et al.
Published: (2025)
PicoAudio: Enabling Precise Timestamp and Frequency Controllability of Audio Events in Text-to-audio Generation
by: Xie, Zeyu, et al.
Published: (2024)
by: Xie, Zeyu, et al.
Published: (2024)
AudioTime: A Temporally-aligned Audio-text Benchmark Dataset
by: Xie, Zeyu, et al.
Published: (2024)
by: Xie, Zeyu, et al.
Published: (2024)
Adaptive Dataset Quantization: A New Direction for Dataset Pruning
by: Yu, Chenyue, et al.
Published: (2025)
by: Yu, Chenyue, et al.
Published: (2025)
PicoAudio2: Temporal Controllable Text-to-Audio Generation with Natural Language Description
by: Zheng, Zihao, et al.
Published: (2025)
by: Zheng, Zihao, et al.
Published: (2025)
FakeSound: Deepfake General Audio Detection
by: Xie, Zeyu, et al.
Published: (2024)
by: Xie, Zeyu, et al.
Published: (2024)
Temperature Scaling Attack Disrupting Model Confidence in Federated Learning
by: Lee, Kichang, et al.
Published: (2026)
by: Lee, Kichang, et al.
Published: (2026)
RoNFA: Robust Neural Field-based Approach for Few-Shot Image Classification with Noisy Labels
by: Xiang, Nan, et al.
Published: (2025)
by: Xiang, Nan, et al.
Published: (2025)
Robust Multivariate Time Series Forecasting against Intra- and Inter-Series Transitional Shift
by: He, Hui, et al.
Published: (2024)
by: He, Hui, et al.
Published: (2024)
AI-Driven Innovations in Modern Cloud Computing
by: Kumar, Animesh
Published: (2024)
by: Kumar, Animesh
Published: (2024)
Enabling Trustworthy Federated Learning in Industrial IoT: Bridging the Gap Between Interpretability and Robustness
by: Jagatheesaperumal, Senthil Kumar, et al.
Published: (2024)
by: Jagatheesaperumal, Senthil Kumar, et al.
Published: (2024)
Redefining Finance: The Influence of Artificial Intelligence (AI) and Machine Learning (ML)
by: Kumar, Animesh
Published: (2024)
by: Kumar, Animesh
Published: (2024)
Unsupervised Elicitation of Moral Values from Language Models
by: Alizadeh, Meysam, et al.
Published: (2026)
by: Alizadeh, Meysam, et al.
Published: (2026)
PairHuman: A High-Fidelity Photographic Dataset for Customized Dual-Person Generation
by: Pan, Ting, et al.
Published: (2025)
by: Pan, Ting, et al.
Published: (2025)
Superior Scoring Rules for Probabilistic Evaluation of Single-Label Multi-Class Classification Tasks
by: Ahmadian, Rouhollah, et al.
Published: (2024)
by: Ahmadian, Rouhollah, et al.
Published: (2024)
Comparative Analysis of Lightweight Deep Learning Models for Memory-Constrained Devices
by: Shahriar, Tasnim
Published: (2025)
by: Shahriar, Tasnim
Published: (2025)
Whole-Song Hierarchical Generation of Symbolic Music Using Cascaded Diffusion Models
by: Wang, Ziyu, et al.
Published: (2024)
by: Wang, Ziyu, et al.
Published: (2024)
AdamHD: Decoupled Huber Decay Regularization for Language Model Pre-Training
by: Guo, Fu-Ming, et al.
Published: (2025)
by: Guo, Fu-Ming, et al.
Published: (2025)
Web-Browsing LLMs Can Access Social Media Profiles and Infer User Demographics
by: Alizadeh, Meysam, et al.
Published: (2025)
by: Alizadeh, Meysam, et al.
Published: (2025)
Reinforced Inverse Scattering
by: Jiang, Hanyang, et al.
Published: (2022)
by: Jiang, Hanyang, et al.
Published: (2022)
Internal noise in hardware deep and recurrent neural networks helps with learning
by: Kolesnikov, Ivan, et al.
Published: (2025)
by: Kolesnikov, Ivan, et al.
Published: (2025)
Conversion rate prediction in online advertising: modeling techniques, performance evaluation and future directions
by: Xue, Tao, et al.
Published: (2025)
by: Xue, Tao, et al.
Published: (2025)
Similar Items
-
Verifiable Dropout: Turning Randomness into a Verifiable Claim
by: Lee, Kichang, et al.
Published: (2025) -
From Benchmarks to Business Impact: Deploying IBM Generalist Agent in Enterprise Production
by: Shlomov, Segev, et al.
Published: (2025) -
When Audio Generators Become Good Listeners: Generative Features for Understanding Tasks
by: Xie, Zeyu, et al.
Published: (2025) -
Any four real numbers are on all fours with analogy
by: Lepage, Yves, et al.
Published: (2024) -
Contemporary Agent Technology: LLM-Driven Advancements vs Classic Multi-Agent Systems
by: Bădică, Costin, et al.
Published: (2025)