Adversarial machine learning
Research field that lies at the intersection of machine learning and computer security
📊 Rating
1 news mentions · 👍 0 likes · 👎 0 dislikes
📌 Topics
- Cybersecurity (1)
- Artificial Intelligence (1)
- Resource Management (1)
🏷️ Keywords
RECUR attack (1) · Large Reasoning Models (1) · Resource exhaustion (1) · Adversarial AI (1) · Chain of Thought (1) · arXiv (1) · Recursive entropy (1)
📖 Key Information
Adversarial machine learning is the study of the attacks on machine learning algorithms, and of the defenses against such attacks.
Machine learning techniques are mostly designed to work on specific problem sets, under the assumption that the training and test data are generated from the same statistical distribution (IID). However, this assumption is often dangerously violated in practical high-stake applications, where users may intentionally supply fabricated data that violates the statistical assumption.
📰 Related News (1)
-
🇺🇸 RECUR: Resource Exhaustion Attack via Recursive-Entropy Guided Counterfactual Utilization and Reflection
arXiv:2602.08214v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) employ reasoning to address complex tasks. Such explicit reasoning requ...
🔗 Entity Intersection Graph
People and organizations frequently mentioned alongside Adversarial machine learning:
- 🌐 Reasoning model (1 shared articles)
- 🌐 Resource exhaustion attack (1 shared articles)
- 🌐 Chain of thought (1 shared articles)