<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Publications &amp; Research on Luciano Maldonado</title>
    <link>https://luciano665.github.io/publications/</link>
    <description>Recent content in Publications &amp; Research on Luciano Maldonado</description>
    <generator>Hugo</generator>
    <language>en-US</language>
    <lastBuildDate>Fri, 25 Sep 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://luciano665.github.io/publications/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>A Deep-Learning Approach for ECG-Based Cryptographic Key Generation</title>
      <link>https://luciano665.github.io/publications/ecg-key-generation/</link>
      <pubDate>Sun, 01 Jun 2025 00:00:00 +0000</pubDate>
      <guid>https://luciano665.github.io/publications/ecg-key-generation/</guid>
      <description>Learning person-specific 256-bit keys from ECG signals with attention to consistency, separation, and statistical randomness.</description>
    </item>
    <item>
      <title>PrivDrift: Auditing User-Secret Leakage Under Topic Drift in Active LLM Conversations</title>
      <link>https://luciano665.github.io/publications/privdrift/</link>
      <pubDate>Fri, 25 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://luciano665.github.io/publications/privdrift/</guid>
      <description>A benchmark for testing whether user-disclosed secrets remain recoverable after a conversation moves to unrelated topics.</description>
    </item>
    <item>
      <title>LLM Sycophancy and Conformal Risk Control</title>
      <link>https://luciano665.github.io/publications/conformal-sycophancy/</link>
      <pubDate>Wed, 01 Apr 2026 00:00:00 +0000</pubDate>
      <guid>https://luciano665.github.io/publications/conformal-sycophancy/</guid>
      <description>Studying harmful agreement in language models and uncertainty thresholds designed to reduce sycophantic responses.</description>
    </item>
    <item>
      <title>Sycophancy in Medical Vision-Language Models</title>
      <link>https://luciano665.github.io/publications/medical-vlm-sycophancy/</link>
      <pubDate>Fri, 11 Sep 2026 00:00:00 +0000</pubDate>
      <guid>https://luciano665.github.io/publications/medical-vlm-sycophancy/</guid>
      <description>Separating failures to perceive a medical image from agreement with a user&amp;rsquo;s spatially false premise.</description>
    </item>
  </channel>
</rss>
