What Lilian Weng thinks about cybersecurity

@lilian-weng · 16 positions · On ppll ↗

Machine-learning researcher; has written the Lil'Log survey posts on how a model technique works since 2017, and worked at OpenAI from 2018 to 2024.

Lilian Weng did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

Filter cybersecurity · Newest first

Topic

All 16LLMs 10cybersecurity 3AI alignment 2design 2neural networks 2reinforcement learning 2AI agents 1AI and human skill 1AI and science 1

4 more topics

computer vision 1recursive self-improvement 1scaling laws 1world models 1

Sort

NewestOldest

Only Lilian Weng on cybersecurity. See everyone on cybersecurity

3 dated positions, 2023 to 2025, in their own words. Our reading of what Lilian Weng has said — not written or endorsed by them.

3 positions so far — this page is not yet offered to search engines.

1. 1 May 2025

   Our readingLonger test-time thinking improves an AI model's robustness to adversarial or unusual inputs.

   Their wordsthinking for longer should be especially useful when the model is presented with an unusual input, such as an adversarial example or jailbreak attempt

   ↗Why We Thinklilianweng.github.io 2nd of 3 in this piece

2. 18 months earlier

3. 25 Oct 2023

   Our readingUniversal adversarial trigger attacks are easy to detect because the learned trigger tokens tend to be nonsensical.

   Their wordsOne drawback with UAT (Universal Adversarial Trigger) attacks is that it is easy to detect them because the learned triggers are often nonsensical.

   ↗Adversarial Attacks on LLMslilianweng.github.io 1st of 2 in this piece

5. 25 Oct 2023

   Our readingHigher-perplexity adversarial attack text is easier to detect and mitigate.

   Their wordsHigh perplexity makes an attack more vulnerable to be detected and mitigated.

   ↗Adversarial Attacks on LLMslilianweng.github.io 2nd of 2 in this piece