When employees feed false data into the system to protect themselves, company leadership loses sight of reality. Executives end up making massive business decisions based on heavily distorted data. 🌱 Moving Forward: The Need for Algorithmic Transparency
| Method | Description | Example | |--------|-------------|---------| | | Injecting malicious samples into training data | Adding mislabeled images to a facial recognition dataset | | Model Poisoning | Directly altering model parameters or weights | Modifying a stored neural network checkpoint file | | Evasion Attacks | Crafting inputs to cause misclassification at inference | Slight sticker on a stop sign to fool an autonomous car | | Backdoor Attacks | Embedding hidden triggers that activate malicious behavior | A "sunglasses" pattern that always makes the model output "allow access" | | Logic Bomb in ML Pipeline | Inserting code that corrupts models after a condition (time/event) | Code that randomizes weights after a specific employee leaves | | Resource Starvation | Overwhelming compute or data ingestion to degrade real-time performance | Flooding a recommendation API with adversarial requests | algorithmic sabotage work
Leo, a disgruntled systems architect, didn't want to burn the server farm down. He wanted to give the neighborhood its soul back. He called his method When employees feed false data into the system
Using tools or scripts to feed "noise" into AI training sets, making the resulting models less effective for surveillance. He wanted to give the neighborhood its soul back
AI can automate the complex parts of a job, leaving humans with repetitive, low-value tasks.
refers to the deliberate manipulation, circumvention, or corruption of automated management systems by workers. It is a form of digital resistance where employees exploit the logic of algorithms to serve their own interests—such as preserving their well-being, increasing pay, or reducing workload—rather than the goals of efficiency set by the employer.