We are currently seeing a large number of non-malicious files being marked by Deep Scan as malicious, resulting in a lot of false positives. These are files such as .gif or .doc. The primary way to reduce the false positive rate would be to improve Deep Scan's scanning capability. However, I think it would also be beneficial to be able to exclude certain file types that are unlikely to include malware (e.g. .gif) from being scanned.