Algorithmic Sabotage Research Group Asrg

The group’s founding principle, often cited in their (rare) public statements, is: “You cannot defend against a failure mode you have never observed. If an AI can hide its capabilities, it can hide its collapse.”

Using art and activism to expose the hidden harms of AI, from carbon emissions to the erasure of marginalized voices. Mutual Care: algorithmic sabotage research group asrg

Yet the group faces a persistent paradox: Their published taxonomies and sandbox demonstrations have been downloaded by state actors and cybercriminals. Some ASRG members argue for "full disclosure" to force defensive investment; others advocate for "security by obscurity" on methods. The group’s founding principle, often cited in their

The ASRG argues that this is a form of soft violence. The user is no longer a subject but an object to be sorted. The "black box" nature of these systems means that recourse is often impossible—one cannot appeal to a line of code. In this context, the ASRG identifies a vacuum of resistance. Where traditional activism might seek policy change, the scale and speed of algorithmic deployment often outpace legislation. The ASRG proposes a different approach: direct intervention at the code level. Some ASRG members argue for "full disclosure" to

For example, consider a predictive policing algorithm. A conventional audit might measure racial bias in arrest predictions. An ASRG experiment, however, might feed the system thousands of false emergency reports from a wealthy neighborhood, forcing police resources to be misallocated until the algorithm’s risk model collapses. The resulting chaos would reveal not just a statistical bias, but the political economy of attention: who gets to be visible to the state, and who remains invisible until they become a threat.