会员服务
Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment
Arxiv
0+阅读 · 6月13日
From ASR to ASP: Evaluating Prompt Attack Vulnerabilities Against Open-Source LLMs
Arxiv
0+阅读 · 6月14日
MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks
Arxiv
0+阅读 · 6月14日
It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents
Arxiv
0+阅读 · 6月4日
Can It Reach the Generator? Investigating the Survival of Prompt-Injection Attacks in Realistic RAG Settings
Arxiv
0+阅读 · 5月28日
Assessing Automated Prompt Injection Attacks in Agentic Environments
Arxiv
0+阅读 · 6月9日
Investigating Detection and Obfuscation of Prompt Injection Attacks Against Software Reverse Engineering AI Agents
Arxiv
0+阅读 · 5月29日
GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines
Arxiv
0+阅读 · 6月7日
PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections
Arxiv
0+阅读 · 6月10日
Misleading Large Language Models used (or misused) in Scientific Peer-Reviewing via Hidden Prompt-Injection Attacks
Arxiv
0+阅读 · 3月30日
Prompt Injection as Role Confusion
Arxiv
0+阅读 · 3月20日
Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks
Arxiv
0+阅读 · 3月31日
AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations
Arxiv
0+阅读 · 3月11日
AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks
Arxiv
0+阅读 · 2月21日
Bypassing AI Control Protocols via Agent-as-a-Proxy Attacks
Arxiv
0+阅读 · 2月25日
参考链接
微信扫码咨询专知VIP会员
Top