ENTITY
Data poisoning attacks against machine learning algorithms
Data poisoning attacks against machine learning algorithms
PulseAugur coverage of Data poisoning attacks against machine learning algorithms — every cluster mentioning Data poisoning attacks against machine learning algorithms across labs, papers, and developer communities, ranked by signal.
Total · 30d
2
2 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
2
2 over 90d
TIER MIX · 90D
TOPICS
RECENT · PAGE 1/1 · 2 TOTAL
-
New theory analyzes data poisoning in continual learning
A new paper introduces a theoretical framework to analyze data poisoning attacks and defenses in continual learning (CL). The research frames the adversary-defender interaction as an online zero-sum game, establishing t…
-
New LLM defense rewrites training data to combat poisoning attacks
Researchers have developed a new defense strategy called Open-Book Benign Rewriting (OBBR) to protect Large Language Models (LLMs) from data poisoning attacks. This method involves rewriting training data to align with …