LESSWRONG
is fundraising!
Tags
LW
$

Computer Security & Cryptography

•

Applied to PoMP and Circumstance: Introduction by benatkin 13d ago

•

Applied to GPT-4o Guardrails Gone: Data Poisoning & Jailbreak-Tuning by ChengCheng 2mo ago

•

Applied to Join the $10K AutoHack 2024 Tournament by Paul Bricman 3mo ago

•

Applied to Secret Collusion: Will We Know When to Unplug AI? by schroederdewitt 3mo ago

•

Applied to Can startups be impactful in AI safety? by Esben Kran 3mo ago

•

Applied to How to Fake Decryption by ohmurphy 4mo ago

•

Applied to Can Large Language Models effectively identify cybersecurity risks? by emile delcourt 4mo ago

•

Applied to The Pragmatic Side of Cryptographically Boxing AI by Bart Jaworski 5mo ago

•

Applied to Freedom and Privacy of Thought Architectures by Ruby 5mo ago

•

Applied to Using an LLM perplexity filter to detect weight exfiltration by Adam Karvonen 5mo ago

•

Applied to Consider attending the AI Security Forum '24, a 1-day pre-DEFCON event by red squiggle 5mo ago

•

Applied to Access to powerful AI might make computer security radically easier by MondSemmel 6mo ago

•

Applied to Disproving and partially fixing a fully homomorphic encryption scheme with perfect secrecy by Lysandre Terrisse 7mo ago

•

Applied to AXRP Episode 30 - AI Security with Jeffrey Ladish by DanielFilan 8mo ago

•

Applied to Cybersecurity of Frontier AI Models: A Regulatory Review by Deric Cheng 8mo ago

•

Applied to End-to-end hacking with language models by tchauvin 9mo ago

•

Applied to 11 diceware words is enough by DanielFilan 10mo ago