Sabotage Research Group Asrg | Algorithmic

In the burgeoning field of Machine Learning (ML) security, most research focuses on defense : robust aggregation, differential privacy, adversarial training, and anomaly detection. A smaller, more provocative, and increasingly vital niche focuses on offense —not to break systems for malice, but to understand their catastrophic failure modes. At the radical fringe of this offensive security research lies the hypothetical (and increasingly real) collective known as the .

The primary mission of ASRG is to advance the state-of-the-art in adversarial machine learning. This involves: algorithmic sabotage research group asrg