Superplatforms are Strategically Compelled to Counteract AI Agents
cs.AI, cs.CY, cs.IR
Submitted: 2025-05-23
Updated: 2026-11-09
Terminology
Sources
- The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections
- Evaluating the Robustness of Multimodal Agents Against Active Environmental Injection Attacks
- Build Agent Advocates, Not Platform Agents
- Certifying LLM Safety against Adversarial Prompting
- EIA: Environmental Injection Attack on Generalist Web Agents for Privacy Leakage
- Caution for the Environment: Multimodal LLM Agents are Susceptible to Environmental Distractions
- BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents
- Foot-In-The-Door: A Multi-turn Jailbreak for LLMs
- AdvAgent: Controllable Blackbox Red-teaming on Web Agents
- A Survey of AI Agent Protocols
- The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)
- Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
- Agentic Information Retrieval
- Attacking Vision-Language Computer Agents via Pop-ups
- QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents