2 papers
cs.LG2026
A Solvable Theory of Pre-training Data Poisoning: Regime-Dependent Scaling Exponents
Indranil Halder, Rastri Dey, Cengiz Pehlevan
Pre-training data poisoning of large language models is usually studied using targeted backdoors and their survival through safety post-training, which leaves open a more basic que…
cs.LG2026
Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover
Indranil Halder, Annesya Banerjee, Cengiz Pehlevan
Adversarial attacks can reliably steer safety-aligned large language models toward unsafe behavior. Empirically, we find that adversarial prompt-injection attacks can amplify attac…