Perplexity Filtering: The First LLM Defense (And Why Evolutionary Attacks Broke It)

In the previous post on evolutionary jailbreaking, I noted that GCG suffixes are “trivially detectable by any perplexity filter.” That line…

Evolving the Jailbreak: How Genetic Algorithms Are Defeating LLM Safety

In July 2023, Zou et al. published a paper that broke open the field of automated LLM jailbreaking [1]. Their method, Greedy Coordinate Grad…

Swarm Intelligence as a Weapon: How Nature-Inspired Algorithms Attack Neural Networks

In a previous post, I covered the one-pixel attack, where differential evolution finds a single pixel change that fools an image classifier.…

Neural Network Visualizer

Demo

An interactive visualization of neural network training with real-time backpropagation animation and decision boundary rendering.

Vigenere Cipher Visualizer

Demo

An interactive visualization of the Vigenere cipher with Kasiski examination cryptanalysis.

Caesar Cipher Visualizer

Demo

An interactive visualization of the Caesar cipher encryption process with frequency analysis cryptanalysis.