The paper builds SOPBench showing frequent SOP violations in agentic browsers and introduces SOPGuard to enforce the policy with low overhead in BrowserOS.
Eia: Environmental injection attack on generalist web agents for privacy leakage
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Frontier browser agents show strong resistance to hand-crafted multi-step prompt injections (0/140 success), unlike coding agents (up to 100%), indicating domain-conditioned safety and that prior high ASR reports may not generalize.
HLL is a new benchmark that evaluates eight frontier multimodal agents on closed-loop interactive CAPTCHA solving, showing sharp performance drops under realism stressors and trace validation.
PIIGuard uses optimized hidden HTML fragments on webpages to block LLMs from leaking contact PII via indirect prompt injection, achieving at least 97% defense success across tested models while preserving benign QA utility.
ARGUS defends LLM agents from context-aware prompt injections by tracking information provenance and verifying decisions against trustworthy evidence, reducing attack success to 3.8% while retaining 87.5% task utility.
ADAM extracts data from LLM agent memory with up to 100% attack success rate by estimating data distribution and selecting queries via entropy guidance.
WARD is a guard model trained on 177K web samples and adversarially hardened via attacker-guard co-evolution to achieve high recall on prompt injections with low false positives and no added latency.
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
citing papers explorer
-
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.