Diffuse or Confuse: A Diffusion Deepfake Speech Dataset
Authors: Anton Firc, Kamil Malinka, Petr Hanáček | Published: 2024-10-09
Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
Authors: Donghyun Lee, Mo Tiwari | Published: 2024-10-09
FreqMark: Frequency-Based Watermark for Sentence-Level Detection of LLM-Generated Text
Authors: Zhenyu Xu, Kun Zhang, Victor S. Sheng | Published: 2024-10-09
Signal Watermark on Large Language Models
Authors: Zhenyu Xu, Victor S. Sheng | Published: 2024-10-09
Hallucinating AI Hijacking Attack: Large Language Models and Malicious Code Recommenders
Authors: David Noever, Forrest McKee | Published: 2024-10-09
Near Exact Privacy Amplification for Matrix Mechanisms
Authors: Christopher A. Choquette-Choo, Arun Ganesh, Saminul Haque, Thomas Steinke, Abhradeep Thakurta | Published: 2024-10-08 | Updated: 2025-03-20
KnowledgeSG: Privacy-Preserving Synthetic Text Generation with Knowledge Distillation from Server
Authors: Wenhao Wang, Xiaoyu Liang, Rui Ye, Jingyi Chai, Siheng Chen, Yanfeng Wang | Published: 2024-10-08 | Updated: 2024-10-10
Superficial Safety Alignment Hypothesis
Authors: Jianwei Li, Jung-Eun Kim | Published: 2024-10-07
SecAlign: Defending Against Prompt Injection with Preference Optimization
Authors: Sizhe Chen, Arman Zharmagambetov, Saeed Mahloujifar, Kamalika Chaudhuri, David Wagner, Chuan Guo | Published: 2024-10-07 | Updated: 2025-01-13
LOTOS: Layer-wise Orthogonalization for Training Robust Ensembles
Authors: Ali Ebrahimpour-Boroojeny, Hari Sundaram, Varun Chandrasekaran | Published: 2024-10-07