Tagged:

2 posts

• Poisoning the Pretraining Corpus: How Attackers Corrupt Foundation Models Before They're Built

  Modern foundation models train on trillions of tokens scraped from the web. Carlini et al. 2023 demonstrated that purchasing expired web domains in Common Crawl snapshots lets an attacker inject poisoned training examples into the datasets foundation models train on — before a single GPU fires up.

  Jul 7, 2026 poisoning-attacks pretraining supply-chain data-security common-crawl foundation-models threat-modeling defense-patterns adversarial-ml

• Federated Learning Poisoning: The Aggregation Attack Surface

  FL aggregation is blind to participant intent. Malicious clients can embed backdoors or reconstruct private training data from gradients.

  Jul 1, 2026 federated-learning poisoning-attacks backdoor privacy threat-modeling defense-patterns gradient-attacks differential-privacy secure-aggregation