WARDEN is a new adversarial training framework for large language models that minimizes worst-case loss over an f-divergence ambiguity set, reducing attack success rates while keeping utility comparable to recent baselines.
Indirect gradient matching for adversarial robust distillation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Information Theoretic Adversarial Training of Large Language Models
WARDEN is a new adversarial training framework for large language models that minimizes worst-case loss over an f-divergence ambiguity set, reducing attack success rates while keeping utility comparable to recent baselines.