Abu Sayed Md. Mostafizur Rahaman
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
Systematic Evaluation of Adversarial Jailbreaking Attacks and Defenses Across Seven Large Language Models
According to the abstract, Md. Robiul Islam Niloy and Abu Sayed Md. Mostafizur Rahaman test five jailbreak attack families on seven language models and four defenses. They report obfuscation attacks succeeded 54.3% of the time on average and that model size did not predict robustness.