1
AI批量轰炸苹果bug赏金计划，审核团队已下线
AI疯狂刷漏洞报告，苹果赏金审核团队被迫下线，自动化攻击敲响安全警钟。
2
Learning to Inject: Automated Prompt Injection via Reinforcement Learning
利用强化学习自动化实现提示注入攻击，性能超越人工红队测试
arXiv:2602.05746v2 Announce Type: replace-cross Abstract: Prompt injection is a critical vulnerability in LLM agents, yet the strongest methods still …
3
JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt Optimization
揭露大模型脆弱性，提出工具辅助迭代优化破解提示的新方法，AI安全攻防前沿研究。
arXiv:2606.11425v1 Announce Type: cross Abstract: Jailbreak attacks expose persistent safety weaknesses in large language models (LLMs), but existing …
4
Assessing Automated Prompt Injection Attacks in Agentic Environments
针对LLM代理的自动化提示注入攻击在真实场景中未被充分研究，本文提供了系统性的实证评估。
arXiv:2606.10525v1 Announce Type: cross Abstract: Indirect prompt injection poses a critical threat to LLM agents that interact with untrusted externa…
5
Automatically Attacking Software Reverse Engineering AI Agents
首项系统化攻击逆向工程AI代理的研究，揭示AI辅助逆向的脆弱性，为安全防御敲响警钟。
arXiv:2605.30667v1 Announce Type: cross Abstract: Software tools for reverse engineering executable binary files, such as Ghidra, enable malware analy…
6
SafeSearch: Automated Red-Teaming of LLM-Based Search Agents
自动化红队测试框架，专攻LLM搜索代理的安全漏洞，已被ICML 2026接收。
arXiv:2509.23694v5 Announce Type: replace Abstract: Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date in…