As machine learning systems have become integrated into safety and security-sensitive applications at exponential speed, the responsible deployment of language models has increasingly presented complex challenges that extend beyond technical implementation: not…
Category: Data Poisoning
A History Of Label-Flipping AI Data Poisoning Attacks
Label-flipping is popular because of key advantages such as requiring not only minimal access to data, but minimal computational resources, as well. In addition to this attack’s low effort and low cost…
A Taxonomy Of AI Training Data Poisoning Attacks
In this brief taxonomy, training data poisoning attacks are divided into the following categories: Bilevel Optimization Poisoning Attacks These attacks frame the poisoning problem as a bilevel optimization where the attacker solves…
A Taxonomy Of AI Data Poisoning Defenses
We begin our taxonomy by dividing data poisoning defenses into three broad categories: Attack Identification Techniques, Attack Repair Techniques, and Attack Prevention Techniques, in which are then organized key research papers by defense type….
The Big List Of AI Data Poisoning Attack And Defense References And Resources
Note that the below are in alphabetical order by title. Enjoy! Thanks for reading!