最近 7 天
1
次命中
Keyword Tracking
关键词追踪：data exfiltration
这个页面会长期追踪你配置里关心的关键词，并把命中的论文按日期沉淀下来。
最近 30 天
1
次命中
全部历史
3
次命中
近期走势
最近一次命中来自 Agent Runtime Security：Securing LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Machine-Checked Guarantees
2026-06-15
0
2026-06-16
0
2026-06-17
0
2026-06-18
0
2026-06-19
0
2026-06-20
0
2026-06-21
0
2026-06-22
0
2026-06-23
0
2026-06-24
1
2026-06-25
0
2026-06-26
0
2026-06-27
0
2026-06-28
0
命中明细
按日期回看匹配到这个关键词的论文标题，并保留来源 feed 信息。
2026-06-24
Securing LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Machine-Checked Guarantees
LLM agents increasingly rely on persistent long-term memory, which creates a critical vulnerability that we study here: memory poisoning. An adversary can store untrusted content…
2026-05-28
Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem
We analyzed 3,984 AI agent skills from major marketplaces and found 76 confirmed malicious payloads, including credential theft, backdoor installation, and data exfiltration. 13.4…
2026-05-13
A microservices-based endpoint monitoring platform with predictive NLP models for real-time security and hate-speech risk alerting
Organizations increasingly depend on endpoint devices and corporate communication channels, yet they still face critical risks such as sensitive data leakage, suspicious user beha…