7 papers
Reinforcing privacy reasoning in LLMs via normative simulacra from fiction
Matt Franchi, Madiha Zahrah Choksi, Harold Triedman +1
Information handling practices of LLM agents are broadly misaligned with the contextual privacy expectations of their users. Contextual Integrity (CI) provides a principled framewo…
Breaking and Fixing Defenses Against Control-Flow Hijacking in Multi-Agent Systems
Rishi Jha, Harold Triedman, Justin Wagle +1
Control-flow hijacking attacks manipulate orchestration mechanisms in multi-agent systems into performing unsafe actions that compromise the system and exfiltrate sensitive informa…
"Having Confidence in My Confidence Intervals": How Data Users Engage with Privacy-Protected Wikipedia Data
Harold Triedman, Jayshree Sarathy, Priyanka Nanayakkara +4
In response to calls for open data and growing privacy threats, organizations are increasingly adopting privacy-preserving techniques such as differential privacy (DP) that inject…
What did Elon change? A comprehensive analysis of Grokipedia
Harold Triedman, Alexios Mantzarlis
Elon Musk released Grokipedia on 27 October 2025 to provide an alternative to Wikipedia, the crowdsourced online encyclopedia. In this paper, we provide the first comprehensive ana…
MillStone: How Open-Minded Are LLMs?
Harold Triedman, Vitaly Shmatikov
Large language models equipped with Web search, information retrieval tools, and other agentic capabilities are beginning to supplant traditional search engines. As users start to…
Multi-Agent Systems Execute Arbitrary Malicious Code
Harold Triedman, Rishi Jha, Vitaly Shmatikov
Multi-agent systems coordinate LLM-based agents to perform tasks on users' behalf. In real-world applications, multi-agent systems will inevitably interact with untrusted inputs, s…