Return-Oriented Programming (ROP) is a sophisticated exploitation technique that is able to drive target applications to perform arbitrary unintended operations by constructing a gadget chain reusing existing small code sequences (gadgets). Existing defense mechanisms either only handle specific types of gadgets, require access to source code and/or a customized compiler, break the integrity of the binary code, or suffer from high performance overhead. In this paper, we present a novel system, ROPecker, to efficiently and effectively defend against ROP attacks without relying on any other side information (e.g., source code and compiler support) or binary rewriting. ROPecker detects an ROP attack at run-time by checking the presence of a sufficiently long chain of gadgets in past and future execution flow, with the assistance of the taken branches recorded in the Last Branch Record (LBR) registers and an efficient technique combining offline analysis with run-time emulation. We also design a sliding window mechanism to invoke the detection logic in proper timings, which achieves both high detection accuracy and efficiency. We build an ROPecker prototype on x86-based Linux computers and evaluate its security effectiveness and performance overhead. In our experiment, ROPecker can detect all ROP attacks from real-world examples and generated by the general-purpose ROP compiler Q. It only incurs acceptable performance overhead on CPU computation, disk I/O and network I/O. ROP Types No Source No Binary Run-time Code Rewriting Efficiency DROP [9] Ret-based √ X X ROPDefender [13] Ret-based √ X X ROPGuard [15] Ret-based √ X √ Return-less Kernel [18] Ret-based X √ √

No abstract

The rowhammer bug is to frequently access hammer rows to induce bit flips in their adjacent victim rows, allowing an attacker to gain privilege escalation or steal private data. A key requirement of all existing rowhammer attacks is that an attacker must have access to at least part of an exploitable hammer row. We refer to such rowhammer attacks as PeriHammer. The stateof-the-art software-only defenses against PeriHammer attacks is to make the exploitable hammer rows beyond the attacker's access permission.In this paper, we question the necessity of the above requirement and propose a new class of rowhammer attacks, termed as TeleHammer. It is a paradigm shift in rowhammer attacks since it crosses privilege boundary to stealthily rowhammer an inaccessible row by implicit DRAM accesses. Such accesses are achieved by abusing inherent features of modern hardware and/or software. We propose a generic model to rigorously formalize the necessary conditions to initiate TeleHammer and PeriHammer, respectively. Compared to PeriHammer, TeleHammer can defeat the advanced software-only defenses, stealthy in hiding itself and hard to be mitigated.To demonstrate the practicality of TeleHammer and its advantages, we have created a TeleHammer's instance, called PThammer, which leverages the address-translation feature of modern processors. We observe that a memory access from user space can induce a load of a Level-1 page-table entry (L1PTE) from memory and thus hammer the L1PTE once, although L1PTE is not accessible to us. To achieve a high enough hammering frequency, we flush relevant TLB and cache effectively and efficiently. To this end, we demonstrate PThammer on three different test machines and show that it can cross user-kernel boundary and induce the first bit flips in L1PTEs within 15 minutes of double-sided PThammering. PThammer does not require the superpage system setting, and works on Ubuntu Linux. We have exploited PThammer to defeat advanced software-only rowhammer defenses in default system setting.

Commodity OS kernels have broad attack surfaces due to the large code base and the numerous features such as device drivers. For a real-world use case (e.g., an Apache Server), many kernel services are unused and only a small amount of kernel code is used. Within the used code, a certain part is invoked only at runtime while the rest are executed at startup and/or shutdown phases in the kernel's lifetime run. In this paper, we propose a reliable and practical system, named KASR, which transparently reduces attack surfaces of commodity OS kernels at runtime without requiring their source code. The KASR system, residing in a trusted hypervisor, achieves the attack surface reduction through a two-step approach: (1) reliably depriving unused code of executable permissions, and (2) transparently segmenting used code and selectively activating them. We implement a prototype of KASR on Xen-4.8.2 hypervisor and evaluate its security effectiveness on Linux kernel-4.4.0-87-generic. Our evaluation shows that KASR reduces the kernel attack surface by 64% and trims off 40% of CVE vulnerabilities. Besides, KASR successfully detects and blocks all 6 real-world kernel rootkits. We measure its performance overhead with three benchmark tools (i.e., SPECINT, httperf and bonnie++). The experimental results indicate that KASR imposes less than 1% performance overhead (compared to an unmodified Xen hypervisor) on all the benchmarks.

No abstract