Registration is 100% Free. We believe everyone deserves access to activities and resources.
A collaborative writing project aimed at conceptualizing strategies of resistance against "algorithmic authoritarianism".
The ASRG’s most concrete contribution to the movement is its ongoing work in curating a list of for digital sabotage. The group actively shares a "curated list of strategies, offensive methods, and tactics for (algorithmic) sabotage, disruption, and deliberate poisoning". These tools are designed to poison training data, disrupt scraping operations, and waste the computational resources of AI companies. Key examples from their list include:
If you'd like, I can provide more details on specific methods like: How to How to create "poisoned" images for AI How to set up a "tarpit" for scrapers
: Published openly across independent literary networks like Reincantamento Substack , this document presents sabotage as an act of solidarity that cuts through capitalist automaticity to build human social autonomy. algorithmic sabotage research group asrg
The group's core ethos is captured in a striking epigraph by an "Anonymous Partisan" that adorns its : " To create? No, to destroy, destroy and destroy again, whatever the strength left in these muscles allows ". While this rhetoric may sound stark, the ASRG is not merely an advocate for digital vandalism. Instead, it positions its work as a form of "techno-disobedience," a necessary counter-power intended to critique, disrupt, and ultimately reclaim agency from what it calls the "algorithmic empire" of surveillance capitalism and automated control.
The theoretical work of the ASRG is deeply tied to physical and digital subcultural media. A prominent example is a zine dedicated to the Algorithmic Sabotage Research Group.
In the rapidly evolving landscape of artificial intelligence (AI) and machine learning (ML), ensuring the reliability and security of algorithms has become a paramount concern. The Algorithmic Sabotage Research Group (ASRG) is at the forefront of this challenge, focusing on the critical examination and enhancement of ML systems' resilience against adversarial attacks. This article provides an in-depth look at the ASRG's mission, methodologies, and contributions to the field of adversarial machine learning. These tools are designed to poison training data,
Rather than just theorizing, ASRG produces actionable tools, zines, and artistic interventions that demonstrate how sabotage can be enacted.
: Resisting automated surveillance, profiling, and discrimination deployed by corporations and state entities.
: A cohort of artists engaged in "cultural red teaming" and creative misuse of AI, which presented at events like DEFCON 31. Anti-Spam Research Group (ASRG) No, to destroy, destroy and destroy again, whatever
At the heart of the group’s activities is the a text distributed internationally under free software guidelines such as the GNU Free Documentation License v1.3. The manifesto reclaims historical notions of worker "sabotage"—traditionally symbolized by the wooden shoe ( sabot ) thrown into industrial machinery—and translates them into the language of code, automation, and neural networks.
The ASRG operates within a broader ecosystem of resistance to surveillance and AI extraction. It has been featured in prestigious European research projects like "Figure It Out," supported by the Creative Europe program, alongside partners such as Drugo More (Croatia), Labomedia (France), and the Unfinished Foundation (Malta). These collaborations help ground the group's radical tactics within the context of transdisciplinary workshops exploring art, science, and technology.
Others have drawn connections between these grassroots efforts and larger state-level operations, noting that state actors are already "poisoning LLMs to great effect" through coordinated disinformation campaigns, suggesting that the methods promoted by the ASRG are not only viable but are already being weaponized on a geopolitical scale.