Full-duplex speech models accept user speech while generating responses, making input timing a potential safety concern. We introduce DuplexJail, which delivers fixed, request-independent spoken jailbreak prompts through the user audio channel. Across four open-source models and 720 harmful requests from AdvBench and H...
Jaechul Roh, Deepak Chandran, Amir Houmansadr et al.· 0 citations
User conversations with large language models (LLMs) often contain highly sensitive personal information that can be exploited by LLM providers to create detailed user dossiers, enable targeted advertising, and train more powerful models. To protect user privacy, anonymizing LLM proxies have emerged as a practical solu...
Dzung Pham, Dillon Sheils, Naina Singh et al.· 0 citations
This work evaluates Overthink on proprietary and open-source reasoning models across the FreshQA, SQuAD, and MuSR datasets, and shows that newer generations of RLMs, while showing a drastic increase in per-token cost, also exhibit up to a 2.3x increase in reasoning tokens, leaving them more vulnerable to Overthink atta...
Abhinav Kumar, Jaechul Roh, Ali Naseh et al.· arXiv.org· 92 citations· ⚡9
It is concluded that agentic surveillance is already easy to implement in practice, and it is called for a comprehensive technical, ethical, and legislative framework to protect users.
Hyejun Jeong, Dzung Pham, Amir Houmansadr et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.