Title: HexPADS: A Platform to Detect “Stealth” Attacks Abstract: Current systems are under constant attack from many different sources. Both local and remote attackers try to escalate their privileges to exfiltrate data or to gain arbitrary code execution. While inline defense mechanisms like DEP, ASLR, or stack canaries are important, they have a local, program centric view and miss some attacks. Intrusion Detection Systems (IDS) use runtime monitors to measure current state and behavior of the system to detect an attack orthogonal to active defenses. Attacks change the execution behavior of a system. Our attack detection system HexPADS detects attacks through divergences from normal behavior using attack signatures. HexPADS collects information from the operating system on runtime performance metrics with measurements from hardware performance counters for individual processes. Cache behavior is a strong indicator of ongoing attacks like rowhammer, side channels, covert channels, or CAIN attacks. Collecting performance metrics across all running processes allows the correlation and detection of these attacks. In addition, HexPADS can mitigate the attacks or significantly reduce their effectiveness with negligible overhead to benign processes.