Selecting a strong cryptographic algorithm makes no sense if the information leaks out of the device through side-channels. Sensitive information, such as secret keys, can be obtained by observing the power consumption, the electromagnetic radiation, etc. This class of attacks are called side-channel attacks. Another type of attacks, namely fault attacks, reveal secret information by inserting faults into the device. Because both side-channel attacks and fault attacks are based on weaknesses in the implementation, they both belong to the category of implementation attacks. This work gives an overview of the state-of-the-art in implementation attacks, reviews the origin of this problem at the CMOS circuit level and discusses countermeasures.