惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

T
Threat Research - Cisco Blogs
C
CERT Recently Published Vulnerability Notes
cs.CL updates on arXiv.org
cs.CL updates on arXiv.org
S
Securelist
K
Kaspersky official blog
V
Vulnerabilities – Threatpost
C
Cisco Blogs
Application and Cybersecurity Blog
Application and Cybersecurity Blog
Hacker News: Ask HN
Hacker News: Ask HN
cs.AI updates on arXiv.org
cs.AI updates on arXiv.org
S
Security Affairs
Forbes - Security
Forbes - Security
Spread Privacy
Spread Privacy
C
CXSECURITY Database RSS Feed - CXSecurity.com
P
Palo Alto Networks Blog
H
Hacker News: Front Page
L
Lohrmann on Cybersecurity
Cloudbric
Cloudbric
S
Schneier on Security
Simon Willison's Weblog
Simon Willison's Weblog
I
InfoQ
人人都是产品经理
人人都是产品经理
PCI Perspectives
PCI Perspectives
月光博客
月光博客
爱范儿
爱范儿
Jina AI
Jina AI
WordPress大学
WordPress大学
N
News and Events Feed by Topic
Cyberwarzone
Cyberwarzone
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
小众软件
小众软件
Google Online Security Blog
Google Online Security Blog
W
WeLiveSecurity
V
V2EX
阮一峰的网络日志
阮一峰的网络日志
美
美团技术团队
博
博客园 - 司徒正美
Scott Helme
Scott Helme
AI
AI
L
LangChain Blog
A
Arctic Wolf
博
博客园 - 【当耐特】
量
量子位
S
SegmentFault 最新的问题
The GitHub Blog
The GitHub Blog
MyScale Blog
MyScale Blog
腾
腾讯CDC
博
博客园 - 叶小钗
Last Week in AI
Last Week in AI
S
Secure Thoughts

Risky Business Features

Fortibleed: The bleeding edge of AI cybercrime What to do 'til the bugpocalypse gets here Mythos on your desk? Using local LLMs for code reviews Pitching security startups to VCs in the AI era How using open weight models can blow up in your face The state of the art in AI model jailbreaks Why NPM v12 won’t stop supply chain attacks Everything is getting much worse, much faster Solo podcast: A deep dive on TeamPCP How to survive supply chain attacks How the CopyFail disclosure went sideways NCSC’s Ollie Whitehouse on surviving the "bugpocalypse" What a great agentic AI deployment plan looks like Mythos smythos! How to find 0day with lesser models Solving the AI agent identity problem Feature Interview: Nicholas Carlini, Anthropic A builder's perspective on Mythos and frontier models Mythos and 0day: Fixing exploits is not safety Mythos and 0day: A hacker’s perspective What happens after North Korea infiltrates? Why CISOs need to be more flexible in the AI era A Risky Biz Experiment: Hunting for iOS 0day with AI Interview: Former NSA and CIA cyber leaders on offensive AI When disaster strykes - Risky Business Media MCP is Dead - Risky Business Media They don't break in, they log in. What's an enterprise to do? A ridiculously deep dive into the Coruna Exploits Being a wartime CISO - Risky Business Media What to do about North Korean remote workers Former Adobe, Cisco and Salesforce CISO talks AI pentesting History Repeats: Security in the AI Agent Era
A deep dive on AI model distillation attacks
James Wilson · 2026-04-29 · via Risky Business Features

Risky Business Features Podcast

April 29, 2026

Presented by

James Wilson

James Wilson

Technology Editor

In this solo episode of Risky Business Features James Wilson explores how distillation techniques are both a legitimate way to train smaller models, as well as a way to steal model capabilities. It’s not just a problem for frontier labs! Any LLM-based product could have its competitive advantage stolen through these attacks.

James covers:

  • High-level concept of distillation
  • Why it matters including close/open-weight/open-source explanation
  • Types of distillation and the prompts used
  • The distillation pipeline end to end
  • Distillation at scale and mitigation techniques
  • Hardware resource constraints for distillation

Your browser does not support the audio element.

A deep dive on AI model distillation attacks

0:00 / 72:08

Logo

Show notes

Self-Instruct: Aligning Language Models with Self-Generated Instructions

Alpaca: A Strong, Replicable Instruction-Following Model

Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality

Orca: Progressive Learning from Complex Explanation Traces of GPT-4

Zephyr: Direct Distillation of LM Alignment

Stealing Part of a Production Language Model

Microsoft probes if DeepSeek-linked group improperly obtained OpenAI data, Bloomberg News reports

Detecting and preventing distillation attacks

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。