7 citations · 8 across the 15 of their papers we have counts for
17 papers
SCARCE: Emergent Institutions in Long-Horizon Multi-Agent Coding Systems
Abhinav Kumar, Rediet Abebe, Eugene Bagdasarian +1
As autonomous agents become widely deployed, coordinating access to shared computing resources and services will become increasingly important. Recent incidents have already reveal…
Sapien: A Stateful Policy Engine for Autonomous AI Agents
Corinn Tiffany, Wen Zhang, Eugene Bagdasarian +1
Contextual security defenses prevent AI agents from taking rogue actions by synthesizing a task-specific policy and enforcing it on the agent's tool calls. In multi-step tasks, how…
Beyond Predictable Paths: Redefining AI Security Incident Reporting for Agents
Anastasia Pustozerova, Eugene Bagdasarian, Luca Beurer-Kellner +22
AI agents are being deployed rapidly, accompanied by a growing number of AI-specific attacks and corresponding incidents. As incident reporting becomes increasingly important for l…
PiSAs: Benchmarking Contextual Integrity in Multi-User Agentic Systems
Shubham Gupta, Nazanin Mohammadi Sepahvand, Abhinav Kumar +6
As LLM agents evolve from single-user assistants into shared organizational infrastructure, new privacy risks emerge: inappropriate information may not only be exposed through outp…
Janus: a Playground for User-Involved Agentic Permission Management
Natalie Grace Brigham, Eugene Bagdasarian, Tadayoshi Kohno +1
AI agents that autonomously execute tool calls on a user's behalf raise pressing questions about permission management: what role could users play, and what role should they play?…
Targeting World Models to Compromise Robot Learning Pipelines
Ethan Rathbun, Ahmed Agha, Saaduddin Mahmud +3
World models have recently seen a rapid growth in both their popularity and capability as more data efficient tools for generating robot training data or simulating real world envi…
AI Snitches Get Glitches: Towards Evading Agentic Surveillance
Hyejun Jeong, Dzung Pham, Amir Houmansadr +1
AI agents are now routinely entrusted with access to users' data and communications, operating with growing autonomy and low human supervision. This increasing reliance on AI agent…
AI Agents May Always Fall for Prompt Injections
Sahar Abdelnabi, Eugene Bagdasarian
Prompt injection is the most critical vulnerability in deployed AI agents. Despite recent progress, we show that the prevailing defense paradigm (data-instruction separation) both…
Contrastive Privacy: A Semantic Approach to Measuring Privacy of AI-based Sanitization
George Bissias, Eugene Bagdasarian, Brian Neil Levine
AI-based sanitization can remove concepts from images and text, but privacy evaluation remains largely ad hoc. We propose contrastive privacy, a formal definition that yields a qua…
SPILLage: Agentic Oversharing on the Web
Jaechul Roh, Eugene Bagdasarian, Hamed Haddadi +1
LLM-powered agents are beginning to automate user's tasks across the open web, often with access to user resources such as emails and calendars. Unlike standard LLMs answering ques…
Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems
Mason Nakamura, Abhinav Kumar, Saswat Das +5
Multi-agent systems, where LLM agents communicate through free-form language, enable sophisticated coordination for solving complex cooperative tasks. This surfaces a unique safety…
Verification Required: The Impact of Information Credibility on AI Persuasion
Saaduddin Mahmud, Eugene Bagdasarian, Shlomo Zilberstein
Agents powered by large language models (LLMs) are increasingly deployed in settings where communication shapes high-stakes decisions, making a principled understanding of strategi…
Persuasion Propagation: Does Persuasion Change AI Agent Behavior?
Hyejun Jeong, Amir Houmansadr, Shlomo Zilberstein +1
AI agents combine normal conversation with autonomous task execution, allowing earlier context to shape how later tasks are executed. Yet studying this possibility is challenging b…
Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies
Mason Nakamura, Abhinav Kumar, Saaduddin Mahmud +3
A multi-agent system (MAS) powered by large language models (LLMs) can automate tedious user tasks such as meeting scheduling that requires inter-agent collaboration. LLMs enable n…
Disappearing Ink: Obfuscation Breaks N-gram Code Watermarks in Theory and Practice
Gehao Zhang, Mingzhe Li, Eugene Bagdasarian +2
Large language models (LLMs) are increasingly used for code generation, making reliable identification of machine-generated code important for attribution, tracking, and misuse det…
Contextual Agent Security: A Policy for Every Purpose
Lillian Tsai, Eugene Bagdasarian
Judging an action's safety requires knowledge of the context in which the action takes place. To human agents who act in various contexts, this may seem obvious: performing an acti…
Self-interpreting Adversarial Images
Tingwei Zhang, Collin Zhang, John X. Morris +2
We introduce a new type of indirect, cross-modal injection attacks against visual language models that enable creation of self-interpreting images. These images contain hidden "met…