Mohamed I University

MLCommons Jailbreak Benchmark v1.0 introduces an end-to-end methodology that evaluates eight open-weight large language models with paired baseline and adversarial conditions using 264 seed prompts spanning eleven hazard categories and representative attacks drawn from the MLCommons Jailbreak Taxonomy, judging responses with the AILuminate Assessment Standard v1.4 and measuring robustness through the Resilience Gap; the unsafe-response rate rose from 11.08% at baseline to 18.65% under jailbreak conditions, yielding an average Resilience Gap of 7.57%, with accessible systems showing a larger mean gap and attack effectiveness varying substantially across attack categories and hazards.

MLCommons Jailbreak Benchmark v1.0 introduces an end-to-end methodology that evaluates eight open-weight large language models with paired baseline and adversarial conditions using 264 seed prompts spanning eleven hazard categories and representative attacks drawn from the MLCommons Jailbreak Taxonomy, judging responses with the AILuminate Assessment Standard v1.4 and measuring robustness through the Resilience Gap; the unsafe-response rate rose from 11.08% at baseline to 18.65% under jailbreak conditions, yielding an average Resilience Gap of 7.57%, with accessible systems showing a larger mean gap and attack effectiveness varying substantially across attack categories and hazards.

This work generates new EGFR inhibitor candidates by fine-tuning a GPT-2 model on roughly 500,000 molecules from the ChEMBL database and benchmarking it against an LSTM network trained on the same dataset, evaluating generated compounds for validity, distinctiveness, and novelty, filtering them by Lipinski's rule of five, synthetic accessibility, and drug-likeness scores, and docking selected candidates against EGFR (PDB ID: 1M17) to assess binding affinity, finding that GPT-2 excels at producing structurally varied molecules while the LSTM generates a larger fraction of chemically valid compounds, with many candidates showing good binding interactions with EGFR.

This work generates new EGFR inhibitor candidates by fine-tuning a GPT-2 model on roughly 500,000 molecules from the ChEMBL database and benchmarking it against an LSTM network trained on the same dataset, evaluating generated compounds for validity, distinctiveness, and novelty, filtering them by Lipinski's rule of five, synthetic accessibility, and drug-likeness scores, and docking selected candidates against EGFR (PDB ID: 1M17) to assess binding affinity, finding that GPT-2 excels at producing structurally varied molecules while the LSTM generates a larger fraction of chemically valid compounds, with many candidates showing good binding interactions with EGFR.