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.
Ad- vweb: Controllable black-box attacks on vlm-powered web agents
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
ShieldNet detects supply-chain poisoned tools in LLM agents by monitoring network interactions with a MITM proxy and lightweight classifier, reaching 0.995 F1 and 0.8% false positives on a new benchmark of 25+ attack types.
Introduces an app-content instrumentation framework and benchmark showing that examined GUI agents suffer 42.0% and 36.1% average misleading rates from third-party content in dynamic and static tests respectively.
Progent introduces a privilege-control framework for AI agents that uses LLM-generated symbolic rules over tools, SMT-solver-enforced monotonic updates, and deterministic checks to reduce attack success rates on AgentDojo and ASB benchmarks.
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 defines Computer-Using Agents for safety analysis, categorizes their threats, proposes a taxonomy of defensive strategies, and summarizes benchmarks and datasets for evaluating CUA safety and performance.
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
LLM agents enable universal interoperability by serving as automatic translators and adapters between proprietary digital services.
citing papers explorer
No citing papers match the current filters.