conftrace_

agent security

8 papers

Explore in graph

Co-occurring keywords · papers mentioning both

prompt injection (3) llm agent (3) large language model (3) autonomous agent (3) failure detection (1) performance degradation (1) agent system (1) defense mechanism (1) security vulnerability (1) security benchmark (1)

Papers

MAPS: A Multilingual Benchmark for Agent Performance and Security EACL 2026 MCPTox: A Benchmark for Tool Poisoning on Real-World MCP Servers AAAI 2026 Towards Capable and Secure Autonomous Computer-Use Agents (Student Abstract) AAAI 2026 VIGIL: Defending LLM Agents Against Tool-Stream Injection via Verify-Before-Commit ACL 2026 Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction Amplification EMNLP 2025 IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents EMNLP 2025 The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents ACL 2025 Everyday Object Meets Vision-and-Language Navigation Agent via Backdoor NeurIPS 2024