The ASRG defines itself as an "aesthetico-political" framework. This means they treat the layout, publication, and presentation of their ideas with the same disruptive energy as the theories themselves. "Theorizing Algorithmic Sabotage" Zines
ASRG specifically targets systems that "reinforce structural injustices". They define these as tools that regulate, harm, or control marginalized communities, often under the guise of efficiency or security. Theorizing Algorithmic Sabotage
In today's digital age, artificial intelligence (AI) and machine learning (ML) are increasingly being integrated into various aspects of our lives. From smart home devices to complex industrial systems, AI-powered algorithms are making decisions that affect us all. However, as these systems become more pervasive, concerns about their reliability, security, and accountability grow. This is where the Algorithmic Sabotage Research Group (ASRG) comes in – a pioneering organization dedicated to investigating the vulnerabilities of AI-powered systems and mitigating the risks associated with their deployment.
The Art of Techno-Disobedience: Inside the Algorithmic Sabotage Research Group (ASRG) algorithmic sabotage research group asrg
Highlighting the physical costs of AI, including carbon emissions and the centralization of control. Radical Perspectives:
The group’s foundational manifesto and accompanying documentation are structured to "systematically subvert the integrity of training pipelines, derail data acquisition procedures, and fundamentally undermine the foundational pillars that uphold the efficacy, reliability, and functionality of AI-driven frameworks".
Corrupting the datasets used to train AI to prevent the development of harmful predictive tools. They define these as tools that regulate, harm,
: A non-profit focused specifically on vehicle security and industry collaboration. Algorithmic Resistance Research Group (ARRG!)
In our latest experiment, we demonstrated how a seemingly innocuous AI-powered recommendation system can be manipulated to produce disastrous results. By injecting carefully crafted "poison" into the system's training data, we were able to cause the algorithm to recommend catastrophic actions in critical situations.
: Investigating how to consciously use sabotage as a means of prefigurative politics against "necropolitical technologies". Militant Algorithmic Agency However, as these systems become more pervasive, concerns
ASRG employs a multifaceted approach to achieve its objectives, including:
: Using community-led direct action to challenge dominant digital monopolies.