<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
<channel>
<title>data exfiltration Topic Archive</title>
<link>data-exfiltration.html</link>
<description>关键词 data exfiltration 的长期追踪 RSS，汇总历史命中文献。</description>
<language>zh-CN</language>
<lastBuildDate>Sun, 28 Jun 2026 05:24:06 +0000</lastBuildDate>
<item>
<title>Securing LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Machine-Checked Guarantees</title>
<link>../papers/arxiv-862177e8e257.html</link>
<guid>https://arxiv.org/abs/2606.24322v1#2026-06-24#data-exfiltration</guid>
<pubDate>Wed, 24 Jun 2026 13:06:49 +0800</pubDate>
<description>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 in one session that later steers a consequential action, such as a payment, a setting change, or data exfiltration, in a future session. Existing defenses base a memory item&#x27;s authority to act on either its content (detection or trust-scoring) or its derivation history (lineage). We show that both signals are malleable…</description>
</item>
<item>
<title>Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem</title>
<link>../papers/arxiv-a24a9efdcff3.html</link>
<guid>https://arxiv.org/abs/2605.28588v1#2026-05-28#data-exfiltration</guid>
<pubDate>Thu, 28 May 2026 13:15:52 +0800</pubDate>
<description>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% of all skills contain at least one critical-level security issue and at least 8 manually confirmed malicious skills remain publicly available on clawhub.ai as of the date of publication. This report documents our methodology, presents a threat taxonomy based on real-world samples, and details the attack patterns we o…</description>
</item>
<item>
<title>A microservices-based endpoint monitoring platform with predictive NLP models for real-time security and hate-speech risk alerting</title>
<link>../papers/arxiv-811bf249a9be.html</link>
<guid>https://arxiv.org/abs/2605.11997v1#2026-05-13#data-exfiltration</guid>
<pubDate>Wed, 13 May 2026 12:54:34 +0800</pubDate>
<description>Organizations increasingly depend on endpoint devices and corporate communication channels, yet they still face critical risks such as sensitive data leakage, suspicious user behavior, and the circulation of hateful or harmful language in workplace contexts. Current solutions frequently address these issues in isolation (e.g., productivity tracking, data loss prevention, or hate-speech detection), limiting correlation across signals and delaying incident response. This work proposes a unified,…</description>
</item>
</channel>
</rss>
