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.
Doomarena: A framework for testing ai agents against evolving security threats
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
An evaluation suite for LLM retail-return agents under ambiguous policy shows frontier models rarely converge on the same resolution.
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.
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.
citing papers explorer
-
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.
-
DRIP-R: A Benchmark for Decision-Making and Reasoning Under Real-World Policy Ambiguity in the Retail Domain
An evaluation suite for LLM retail-return agents under ambiguous policy shows frontier models rarely converge on the same resolution.
-
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.
-
Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.
- Signal-Driven Observation for Long-Horizon Web Agents
- Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain