Year | Venue | Title | Authors | Citations | |
|---|---|---|---|---|---|
| 2025 | arXiv.org | Cracks in The Stack: Hidden Vulnerabilities and Licensing Risks in LLM Pre-Training Datasets | 0 | ||
| 2025 | arXiv.org | Auditing Prompt Caching in Language Model APIs | 0 | ||
| 2025 | arXiv.org | The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text | 0 | ||
| 2025 | arXiv.org | A General Pseudonymization Framework for Cloud-Based LLMs: Replacing Privacy Information in Controlled Text Generation | 0 | ||
| 2025 | arXiv.org | Unveiling Privacy Risks in LLM Agent Memory | 0 | ||
| 2025 | arXiv.org | Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System | 0 | ||
| 2025 | arXiv.org | Typographic Attacks in a Multi-Image Setting | 0 | ||
| 2025 | arXiv.org | Topic-FlipRAG: Topic-Orientated Adversarial Opinion Manipulation Attacks to Retrieval-Augmented Generation Models | 0 | ||
| 2025 | arXiv.org | Rerouting LLM Routers | 0 | ||
| 2025 | arXiv.org | Image-based Multimodal Models as Intruders: Transferable Multimodal Attacks on Video-based MLLMs | 1 |