Lorazepam is extensively used to treat anxiety disorders and anxiety associated with depression. This study evaluates the safety of lorazepam based on real-world data from the U.S. Food and Drug Administration Adverse Event Reporting System (FAERS). Data were collected from January 2004 to June 2024. After standardizing the data, we quantified signals using four algorithms, including the Reporting Odds Ratio (ROR), the Proportional Reporting Ratio (PRR), the Bayesian Confidence Propagation Neural Network (BCPNN), and the Multi-Item Gamma Poisson Shrinker (MGPS) to quantize the signal by Bayesian analysis and disproportionation analysis. AE signals were predominantly involved psychiatric disorders, nervous system disorders, injury, poisoning and procedural complications, and cardiac disorders. Notably, new potential AE signals of clinical value were identified in this study, including tachycardia, rhabdomyolysis, neologism, phagophobia, pancreatic fibrosis, and pneumonia. Sex-stratified analysis showed that the risk of poisoning was more pronounced in females and the AEs of sedation were more pronounced in males. Age-stratified analysis demonstrated variations in AEs across different age groups.The findings of this study were consistent with clinical trials, and identified several new potential AE signals. In addition, there are gender and age differences in some AEs. These findings provide valuable insights into lorazepam in clinical practice.