DRIP-R is a new benchmark showing that frontier LLMs systematically disagree on how to resolve identical ambiguous retail policy scenarios, highlighting ambiguity as a core challenge for agent decision-making.
Doomarena: A framework for testing ai agents against evolving security threats
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
Agentic browsers are vulnerable to 20 web and LLM attacks with 18 implemented, exposing five failure modes across four major LLM models that require redesign before safe deployment.
The paper defines and evaluates Trojan Hippo attacks on LLM agent memory, showing 85-100% success in data exfiltration across backends and reduced rates with defenses at varying utility costs.
Adversaries can poison finetuning data, base models, or environments to backdoor AI agents, achieving over 80% success in leaking confidential information on two agentic benchmarks.
citing papers explorer
-
DRIP-R: A Benchmark for Decision-Making and Reasoning Under Real-World Policy Ambiguity in the Retail Domain
DRIP-R is a new benchmark showing that frontier LLMs systematically disagree on how to resolve identical ambiguous retail policy scenarios, highlighting ambiguity as a core challenge for agent decision-making.
-
WAAA! Web Adversaries Against Agentic Browsers
Agentic browsers are vulnerable to 20 web and LLM attacks with 18 implemented, exposing five failure modes across four major LLM models that require redesign before safe deployment.
-
Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration
The paper defines and evaluates Trojan Hippo attacks on LLM agent memory, showing 85-100% success in data exfiltration across backends and reduced rates with defenses at varying utility costs.
-
Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain
Adversaries can poison finetuning data, base models, or environments to backdoor AI agents, achieving over 80% success in leaking confidential information on two agentic benchmarks.