5 citations · 10 across the 7 of their papers we have counts for
10 papers
ToolRosetta: Surface-Form Invariance of Tool-Call Guards
Hasan Demirkiran, Jens Ernstberger
Step-level guards for tool-using agents are evaluated on tidy JSON tool calls, but deployed coding agents act through execute_bash and execute_code tools whose payloads are strings…
Language Is a Security Surface for Agent Guards
Hasan Demirkiran, Jens Ernstberger
Step-level guards decide, before each tool call, whether an agent's next action is safe given the user's request and the trajectory so far. Users write those requests in many langu…
Shortcut Sensitivity in Agent-Safety Evaluations
Hasan Demirkiran, Jens Ernstberger
AI agents take actions through tools. Some actions are sensitive, so guards that supervise them must themselves be evaluated reliably. Yet the data used to evaluate a guard can inc…
What Does It Take to Detect an AI Agent? Minimal Feature Sets for Behavioral Detection under Browser Automation
Vishisht Choudhary, Lukas Schmidt, Anne Zoë Kenntner +3
Bot detectors deployed at scale treat traffic as binary: human or bot. This assumption breaks when AI agents browse the web through browser automation, a traffic class that is neit…
Incentive-Compatible Recovery from Manipulated Signals, with Applications to Decentralized Physical Infrastructure
Jason Milionis, Jens Ernstberger, Joseph Bonneau +2
We introduce the first formal model capturing the elicitation of unverifiable information from a party (the "source") with implicit signals derived by other players (the "observers…
Zero-Knowledge Location Privacy via Accurate Floating-Point SNARKs
Jens Ernstberger, Chengru Zhang, Luca Ciprian +2
We introduce Zero-Knowledge Location Privacy (ZKLP), enabling users to prove to third parties that they are within a specified geographical region while not disclosing their exact…
SoK: What don't we know? Understanding Security Vulnerabilities in SNARKs
Stefanos Chaliasos, Jens Ernstberger, David Theodore +3
Zero-knowledge proofs (ZKPs) have evolved from being a theoretical concept providing privacy and verifiability to having practical, real-world implementations, with SNARKs (Succinc…
Blockchain Censorship
Anton Wahrstätter, Jens Ernstberger, Aviv Yaish +8
Permissionless blockchains promise to be resilient against censorship by a single entity. This suggests that deterministic rules, and not third-party actors, are responsible for de…
Mitigating Decentralized Finance Liquidations with Reversible Call Options
Kaihua Qin, Jens Ernstberger, Liyi Zhou +2
Liquidations in Decentralized Finance (DeFi) are both a blessing and a curse -- whereas liquidations prevent lenders from capital loss, they simultaneously lead to liquidation spir…
SoK: Decentralized Finance (DeFi) Attacks
Liyi Zhou, Xihan Xiong, Jens Ernstberger +7
Within just four years, the blockchain-based Decentralized Finance (DeFi) ecosystem has accumulated a peak total value locked (TVL) of more than 253 billion USD. This surge in DeFi…