会员服务
MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks
Arxiv
0+阅读 · 2月9日
Meta SecAlign: A Secure Foundation LLM Against Prompt Injection Attacks
Arxiv
0+阅读 · 2月6日
AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks
Arxiv
0+阅读 · 2月14日
AgentDyn: A Dynamic Open-Ended Benchmark for Evaluating Prompt Injection Attacks of Real-World Agent Security System
Arxiv
0+阅读 · 2月6日
Bypassing AI Control Protocols via Agent-as-a-Proxy Attacks
Arxiv
0+阅读 · 2月4日
Clouding the Mirror: Stealthy Prompt Injection Attacks Targeting LLM-based Phishing Detection
Arxiv
0+阅读 · 2月5日
Defending Against Prompt Injection with DataFilter
Arxiv
0+阅读 · 2月4日
WebSentinel: Detecting and Localizing Prompt Injection Attacks for Web Agents
Arxiv
0+阅读 · 2月3日
AgentDyn: A Dynamic Open-Ended Benchmark for Evaluating Prompt Injection Attacks of Real-World Agent Security System
Arxiv
0+阅读 · 2月3日
ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents
Arxiv
0+阅读 · 1月30日
Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems
Arxiv
0+阅读 · 1月24日
Prompt Injection Mitigation with Agentic AI, Nested Learning, and AI Sustainability via Semantic Caching
Arxiv
0+阅读 · 1月19日
PIShield: Detecting Prompt Injection Attacks via Intrinsic LLM Features
Arxiv
0+阅读 · 1月24日
ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack
Arxiv
0+阅读 · 1月15日
PINA: Prompt Injection Attack against Navigation Agents
Arxiv
0+阅读 · 1月20日
参考链接
微信扫码咨询专知VIP会员
Top